Memory-related vulnerabilities often result in system crashes and performance drops, imposing significant risks for embedded systems. Despite the potential of Language Models (LMs) in program repair, existing LM-based approaches struggle with these vulnerabilities due to two primary limitations: i) LMs do not possess adequate domain knowledge concerning program analysis and the characteristics of memory-related vulnerabilities, and ii) LMs face constraints in managing contexts as the size of programs increases. To address this issue, we introduce MVRepair, a novel lightweight Language Model (ℓLM)-driven framework built upon a domain-specific knowledge library that is developed through the examination of 7,935 real-world memory-related vulnerabilities. By using our proposed knowledge-based analysis strategy and semantic-guided segmentation mechanism, MVRepair can substantially enhance the LM’s ability to repair programs with memory-related vulnerabilities. Comprehensive experimental results on 8,118 real-world memory-related vulnerabilities demonstrate that, compared with state-of-the-art LM-based approaches, MVRepair yields improvements of a minimum of 23.8% in EM, 31.9% in BLEU-4, and 16.7% in CodeBLEU.

Along with the prosperity of Artificial Intelligence (AI) and Internet of Things (IoT) techniques, Split Federated Learning (SFL) is becoming popular in designing Artificial Intelligence of Things (AIoT) applications, since it enables knowledge sharing among resource-constrained devices without compromising data privacy. By offloading a portion of the full model onto cloud servers, SFL can not only enable AIoT devices to accommodate large models beyond their capabilities, but also reduce their overall local training efforts. However, due to various inherent data and device heterogeneity issues, existing SFL methods greatly suffer from low inference performance and slow convergence, especially when the network bandwidth of devices is limited. To address these problems, this paper presents a novel SFL approach named Sliding Split Federated Learning (S2FL). Unlike traditional SFL methods that train the same portion of models on each device, S2FL maintains different model portions on heterogeneous AIoT devices adaptively according to their current computing capability and network bandwidth based on our proposed adaptive model sliding split method, which can balance the training time between devices and mitigate the notorious straggler problem caused by devices with weak computation power and long network transmission time. Meanwhile, based on our proposed data balance-aware training mechanism, S2FL enables the training of the server model portion on the balanced local data of grouped devices, thus alleviating the degradation of inference accuracy caused by data heterogeneity. Comprehensive experimental results highlight the superiority of S2FL over conventional SFL methods, where S2FL can achieve up to 11.58% inference accuracy improvement and 3.82× training acceleration.

The integration of Energy Harvesting (EH) technology into Mobile Edge Computing (MEC) presents a promising solution to the energy limitations faced by end devices (EDs) when performing computation-intensive tasks, ultimately enhancing the EDs’ sustainability. However, the intermittent and unpredictable nature of harvested energy introduces significant uncertainty in energy availability, complicating dynamic task execution and resource management. In EH-MEC systems, managing task scheduling and offloading dynamically is crucial for optimizing application latency while ensuring long-term battery energy stability and task reliability. Existing approaches inadequately address the time-coupling between task decisions caused by long-term battery energy stability constraints, and often neglect task reliability considerations. To overcome these limitations, we propose decomposing the original problem into 1) a decoupling problem that transforms the optimization with long-term battery energy constraints into a series of deterministic optimizations within individual time slots, 2) a task scheduling problem that determines task-to-ES assignment and computing resource allocation of ESs to offloaded tasks, and 3) a task offloading problem that determines the optimal offloading decision to achieve minimal latency while meeting energy stability and server reliability constraints. To tackle these subproblems, we design a Lyapunov-based optimization method, a reliabilityaware task scheduling algorithm, and an efficient heuristic-based task offloading algorithm. Extensive simulations and experiments based on empirical data from a physical MEC testbed validate the efficacy of our approach.

Although Split Federated Learning (SFL) effectively enables knowledge sharing among resource-constrained clients, it suffers from low training performance due to the neglect of data heterogeneity and catastrophic forgetting problems. To address these issues, we propose a novel SFL approach named MultiSFL, which adopts i) an effective multi-model aggregation mechanism to alleviate gradient divergence caused by heterogeneous data and ii) a novel knowledge replay strategy to deal with the catastrophic forgetting problem. MultiSFL adopts two servers (i.e., the fed server and main server) to maintain multiple branch models for local training and an aggregated master model for knowledge sharing among branch models. To mitigate catastrophic forgetting, the main server of MultiSFL selects multiple assistant devices for knowledge replay according to the training data distribution of each full branch model. Experimental results obtained from various non-IID and IID scenarios demonstrate that MultiSFL significantly outperforms conventional SFL methods by up to a 23.25% test accuracy improvement.

Due to the lack of data auditing techniques for untrusted clients, Federated Learning (FL) is vulnerable to backdoor attacks.Although various methods have been proposed to protect FL against backdoor attacks, they still exhibit poor defense performance in extreme data heterogeneity scenarios.Worse still, these methods strongly rely on additional datasets, violating the privacy protection requirements of FL.To overcome the above shortcomings, this paper proposes a novel data-free backdoor defense approach for FL, named FilterFL, which strives to prevent uploaded client models with backdoor knowledge from participating in the aggregation operation in each FL communication round.Based on our knowledge extraction and backdoor filtering schemes using two well-designed Conditional Generative Adversarial Networks (CGANs), FilterFL extracts incremental knowledge learned by a newly updated global model and filters its backdoor components, which can be used to generate one sample that reflects backdoor knowledge for each category.If an uploaded local model can confidently classify a generated sample into its target category, the knowledge contributed by the model will be excluded from the aggregation.In this way, FilterFL can effectively defend against backdoor attacks without using any additional auxiliary data.Comprehensive experiments on well-known datasets demonstrate that, compared with state-of-the-art methods, our approach achieves the best defense performance within various data heterogeneity scenarios.

Due to the power of learning representations from unlabeled graphs, graph contrastive learning (GCL) has shown excellent performance in community detection tasks. Existing GCL-based methods on the community detection usually focused on learning attribute representations of individual nodes, which, however, ignores structure semantics of communities (e.g., nodes in the same community should be structurally cohesive). Therefore, in this paper, we consider the community detection under the community structure semantics and propose an effective framework for graph contrastive learning under structure semantics (GCLS2) to detect communities. To seamlessly integrate interior dense and exterior sparse characteristics of communities with our contrastive learning strategy, we employ classic community structures to extract high-level structural views and design a structure semantic expression module to augment the original structural feature representation. Moreover, we formulate the structure contrastive loss to optimize the feature representation of nodes, which can better capture the topology of communities. To adapt to large-scale networks, we design a high-level graph partitioning (HGP) algorithm that minimizes the community detection loss for GCLS2 online training. It is worth noting that we prove a lower bound on the training of GCLS2 from the perspective of the information theory, explaining why GCLS2 can learn a more accurate representation of the structure. Extensive experiments have been conducted on various real-world graph datasets and confirmed that GCLS2 outperforms nine state-of-the-art methods, in terms of the accuracy, modularity, and efficiency of detecting communities.

Along with the prosperity of Artificial Intelligence (AI) techniques, more and more Artificial Intelligence of Things (AIoT) applications adopt Federated Learning (FL) to enable collaborative learning without compromising the privacy of devices. Since existing centralized FL methods suffer from the problems of single-point-offailure and communication bottleneck caused by the parameter server, we are witnessing an increasing use of Decentralized Federated Learning (DFL), which is based on Peer-to-Peer (P2P) communication without using a global model. However, DFL still faces three major challenges, i.e., limited computing power and network bandwidth of resource-constrained devices, non-Independent and Identically Distributed (non-IID) device data, and all-neighbor-dependent knowledge aggregation operations, all of which greatly suppress the learning potential of existing DFL methods. To address these problems, this paper presents an efficient DFL framework named MMDFL based on our proposed multi-model-based learning and knowledge aggregation mechanism. Specifically, MMDFL adopts multiple traveler models, which perform local training individually along their traversed devices, accelerating and maximizing knowledge learning and sharing among devices. Moreover, based on our proposed device selection strategy, MMDFL enables each traveler to adaptively explore its next best neighboring device to further enhance the DFL training performance, taking into account issues of data heterogeneity, limited resources and catastrophic forgetting phenomenon. Experimental results from simulation and a real testbed show that, compared with state-of-the-art DFL methods, MMDFL can not only significantly reduce the communication overhead but also achieve better overall classification performance for both IID and non-IID scenarios.

Although Federated Fine-Tuning (FFT) facilitates the fine-tuning of Large Language Models (LLMs) across data owners without compromising their privacy, it suffers from severe communication overheads caused by numerous parameters of LLMs even with Parameter-Efficient Fine-Tuning (PEFT) methods. To address this, we propose a novel communication-efficient FFT framework by reducing per-round transmission costs and simultaneously diminishing the required convergence rounds. Specifically, we freeze the parameter-intensive backbone of LLMs, activate low-rank adapters for fine-tuning, and design a parameter quantization mechanism to reduce per-round communication costs. Additionally, inspired by in-context learning, we align the distributions of local data by identifying and rewriting unimportant samples using the global model, retaining important local information, and guiding local fine-tuning towards a uniform trajectory, thereby accelerating convergence and reducing transmission burdens. Experiments on two instruction datasets show that our method can reduce communication costs by up to 7.76× without compromising performance.

Due to the absence or mismatch of semantic information, existing few-shot image generation methods suffer from unsatisfactory generation quality and diversity, which have minimal benefits as data augmentation for downstream classification tasks. Reformatting the contextual and textural information of features at different scales, we propose a novel Feature Equalization Fusion Generative Adversarial Network (EqGAN) for few-shot image generation. Specifically, we first decompose the encoded features into textual and structural components to mitigate the influence of irrelevant and redundant information. Based on feature correlation learning and attention mechanism, we then obtain fused features by refining different contents (i.e., textures and structures) with a more fine-grained semantic alignment. Moreover, an attention-based reconstruction loss and a consistency-based equalization loss are devised to provide better training stability and generation performance. Comprehensive experiments on three public datasets demonstrate that EqGAN not only significantly improves the FID scores (by up to 14.10%) and LPIPS scores (by up to 3.17%) of generated images, but also outperforms the state-of-the-art in terms of accuracy (by up to 3.89%) for downstream classification.

Due to the semantic entanglement in fusion strategies or unstable training in complicated image transformations, existing few-shot image generation methods still suffer from low generation quality and diversity. To tackle the above problems, we propose a novel fusion- and transformation-based framework named content Fusion with style Transformation Generative Adversarial Network (FiTGAN) for few-shot image generation. The basic assumption is that any image consists of a collection of content-related and style-related features. FiTGAN disentangles internal representations with two independent encoders and combines the fused contents and transformed styles to generate new images. Specifically, we design a multi-scale content fusion strategy and a reparameterized style transformation mechanism to learn more fine-grained semantics without changing category-relevant attributes. Furthermore, we formulate a content reconstruction loss and a style divergence loss to provide better training stability and generation performance. Comprehensive experiments on three well-known datasets demonstrate that FiTGAN can not only produce more realistic and diverse images for few-shot image generation but also achieve better classification accuracy for downstream visual applications with limited data.

Group Equivariant Convolution (GConv) empowers models to explore underlying symmetry in data, improving performance. However, real-world scenarios often deviate from ideal symmetric systems caused by physical permutation, characterized by non-trivial actions of a symmetry group, resulting in asymmetries that affect the outputs, a phenomenon known as Symmetry Breaking. Traditional GConv-based methods are constrained by rigid operational rules within group space, assuming data remains strictly symmetry after limited group transformations. This limitation makes it difficult to adapt to Symmetry-Breaking and non-rigid transformations. Motivated by this, we mainly focus on a common scenario: Rotational Symmetry-Breaking. By relaxing strict group transformations within Strict Rotation-Equivariant group $\mathbf{C}_n$, we redefine a Relaxed Rotation-Equivariant group $\mathbf{R}_n$ and introduce a novel Relaxed Rotation-Equivariant GConv (R2GConv) with only a minimal increase of $4n$ parameters compared to GConv. Based on R2GConv, we propose a Relaxed Rotation-Equivariant Network (R2Net) as the backbone and develop a Relaxed Rotation-Equivariant Object Detector (R2Det) for 2D object detection. Experimental results demonstrate the effectiveness of the proposed R2GConv in natural image classification, and R2Det achieves excellent performance in 2D object detection with improved generalization capabilities and robustness. The code is available in \texttt{https://github.com/wuer5/r2det}.

Dataset 1: ETH-UCY [2] [3] dataset: ETH-UCY consists of the following sub-datasets: ETH, HOTEL, UNIV, ZARA1, ZARA2. In accordance with previous research experimental setups, we split each trajectory sample into 8-second segments, using a time interval of 0.4 seconds. We use the first 3.2 seconds (8 steps) of trajectory data to predict the next 4.8 seconds (12 steps). For training, we use a leave-one-out strategy with 4 subsets and the remaining subset for testing.

Crystal structures can be simplified as a periodic point set that repeats across three-dimensional space along an underlying lattice. Traditionally, crystal representation methods rely on descriptors such as lattice parameters, symmetry, and space groups to characterize the structure. However, in reality, atoms in materials always vibrate above absolute zero, causing their positions to fluctuate continuously. This dynamic behavior disrupts the fundamental periodicity of the lattice, making crystal graphs based on static lattice parameters and conventional descriptors discontinuous under slight perturbations. Chemists proposed the pairwise distance distribution (PDD) method to address this. However, the completeness of PDD requires defining a large number of neighboring atoms, leading to high computational costs. Additionally, PDD does not account for atomic information, making it challenging to apply it directly to crystal material property prediction tasks. To tackle these challenges, we introduce the atom-weighted Pairwise Distance Distribution (WPDD) and Unit cell Pairwise Distance Distribution (UPDD) for the first time, applying them to the construction of multi-edge crystal graphs. We demonstrate the continuity and general completeness of crystal graphs under slight atomic position perturbations. Moreover, by modeling PDD as global information and integrating it into matrix-based message passing, we significantly reduce computational costs. Comprehensive evaluation results show that WPDDFormer achieves state-of-the-art predictive accuracy across tasks on benchmark datasets such as the Materials Project and JARVIS-DFT.

As a promising privacy-aware collaborative model training paradigm, Federated Learning (FL) is becoming popular in the design of distributed recommender systems. However, Federated Recommender Systems (FedRecs) greatly suffer from two major problems: i) extremely high communication overhead due to massive item embeddings involved in recommendation systems, and ii) intolerably low training efficiency caused by the entanglement of both heterogeneous network environments and client devices. Although existing methods attempt to employ various compression techniques to reduce communication overhead, due to the parameter errors introduced by model compression, they inevitably suffer from model performance degradation. To simultaneously address the above problems, this paper presents a communication-efficient FedRec framework named FedRAS, which adopts an action-sharing strategy to cluster the gradients of item embedding into a specific number of model updating actions for communication rather than directly compressing the item embeddings. In this way, the cloud server can use the limited actions from clients to update all the items. Since gradient values are significantly smaller than item embeddings, constraining the directions of gradients (i.e., the action space) introduces smaller errors compared to compressing the entire item embedding matrix into a reduced space. To accommodate heterogeneous devices and network environments, FedRAS incorporates an adaptive clustering mechanism that dynamically adjusts the number of actions. Comprehensive experiments on well-known datasets demonstrate that FedRAS can reduce the size of communication payloads by up to 96.88%, while not sacrificing recommendation performance within various heterogeneous scenarios. We have open-sourced FedRAS at https://github.com/mastlab-T3S/FedRAS.

Although Federated Learning (FL) is promising in privacy-preserving collaborative model training, it faces low inference performance due to heterogeneous data among clients. Due to heterogeneous data in each client, FL training easily learns the specific overfitting features. Existing FL methods adopt the coarse-grained average aggregation strategy, which causes the global model to easily get stuck in local optima, resulting in low generalization of the global model. Specifically, this paper presents a novel FL framework named FedPhoenix to address this issue, which stochastically resets partial parameters to destroy some features of the global model in each round to guide the FL training to learn multiple generalized features for inference rather than specific overfitting features. Experimental results on various well-known datasets demonstrate that compared to SOTA FL methods, FedPhoenix can achieve up to 20.73\% accuracy improvement.

Autonomous machines often encounter complex timing constraints, such as those concerning end-to-end timing guarantees and real-time data fusion, etc. Tasks are often event-triggered or time-triggered at varying rates and exhibit data dependencies in between. Maintaining the real-time performance of autonomous machines becomes a highly challenging endeavor. In this paper, we formulate the workload of an autonomous machine as a hybrid Directed Acyclic Graph (DAG), which contains both time-trigger tasks and event-trigger tasks, with a distinct focus on the task of ensuring timing consistency in data fusion and adherence to end-to-end constraints within the DAG model. We design a concise mechanism to select suitable data received by a node and transmit them to successor nodes. This ensures both the timing disparity—as reflected by the differences in timestamps of the data used for fusion—and the end-to-end latency from the sensor to the controller is confined within a certain boundary. The proposed method is proven to be optimal as it always selects suitable data to guarantee the timing correctness of an autonomous machine as far as it (inherently) has the capacity. Experimental results show that our method can significantly improve the success rate of guaranteeing both timing consistency and end-to-end constraints of the autonomous machine.

Although various methods are proposed to generate music accompaniment tracks according to the main music track, they suffer from the problems of modeling music dependencies and representing music data, therefore, generating high-quality music accompaniment remains a challenging task.To address this issue, we propose a multi-track sequential convolutional neural network (MuseCNN) to generate accompaniment tracks corresponding to the main music track.Inspired by the similarity between pianoroll representation and pictures, we transform the pianoroll data into a two-channel music representation matrix and feed it into the convolutional neural network (CNN).Using a hierarchical loss function, we integrate all music tracks to maintain the coherence and harmony of the music.Based on the three-level loss design and multiple CNNs, the problem of modeling music dependencies can be solved.The experimental results indicate that our multi-CNN model can effectively learn complex music dependencies and generate harmonious longsequence polyphonic music.

In many real-world applications such as social network analysis, knowledge graph discovery, biological network analytics, and so on, graph data management has become increasingly important and has drawn much attention from the database community. While many graphs (e.g., Twitter, Wikipedia, etc.) are usually evolving over time, it is of great importance to study the continuous subgraph matching (CSM) problem, a fundamental, yet challenging, graph operator, which continuously monitors subgraph matching results over dynamic graphs with a stream of edge updates. To efficiently tackle the CSM problem, we carefully design a general CSM processing framework, based on novel DynamIc Vertex DomINance Embedding (DIVINE), which maps vertex neighborhoods into an embedding space to enable efficient subgraph matching and incremental maintenance under dynamic updates. Inspired by low pruning power for high-degree vertices, we propose a new degree grouping technique to decompose high-degree star patterns into groups of lower-degree star substructures, and devise degree-aware star substructure synopses (DAS 3 ) over embeddings of star substructure groups. We develop efficient algorithms to incrementally maintain dynamic graphs and answer CSM queries by traversing DAS 3 synopses and applying our designed vertex dominance and range pruning strategies. Through extensive experiments, we confirm the efficiency of our proposed DIVINE approach over both real and synthetic graphs.

For the past decades, the subgraph similarity search over a large-scale data graph has become increasingly important and crucial in many real-world applications, such as social network analysis, bioinformatics network analytics, knowledge graph discovery, and many others. While previous works on subgraph similarity search used various graph similarity metrics such as the graph isomorphism, graph edit distance, and so on, in this paper, we propose a novel problem, namely subgraph similarity search under aggregated neighbor difference semantics (S 3 AND), which identifies subgraphs g in a data graph G that are similar to a given query graph q by considering both keywords and graph structures (under new keyword/structural matching semantics). To efficiently tackle the S 3 AND problem, we design two effective pruning methods, keyword set and aggregated neighbor difference lower bound pruning , which rule out false alarms of candidate vertices/subgraphs to reduce the S 3 AND search space. Furthermore, we construct an effective indexing mechanism to facilitate our proposed efficient S 3 AND query answering algorithm. Through extensive experiments, we demonstrate the effectiveness and efficiency of our S 3 AND approach over both real and synthetic graphs under various parameter settings.

Over the past few years, the integration of mobile edge computing (MEC) and serverless computing, known as serverless MEC (SMEC), has garnered considerable attention. Despite abundant existing works on SMEC exploration, there remains an unaddressed gap in guaranteeing dependable application outputs due to ignoring the threat of both soft and bit errors on SMEC infrastructures. Furthermore, existing works fall short of accommodating the personalized requirements and approximate computation of Internet of Things (IoT) applications, thereby resulting in holistic quality-of-service (QoS) degradation of SMEC systems typically provisioned by limited edge resources. In this article, we investigate the reliability-aware personalized deployment of approximate computation IoT applications for QoS maximization in SMEC environments. To this end, we propose a hybrid methodology composed of offline and online optimization phases. At the offline phase, a decomposition-based function placement method is devised to accomplish function-to-server mapping by integrating convex optimization, cross-entropy method, and incremental control techniques. At the online phase, a lightweight reinforcement learning scheme based on proximal policy optimization (PPO) is developed to handle the inherent dynamicity of IoT applications. We also build a simulation platform upon the real-world base station distribution in Shanghai Telecom and the practical cluster trace in the Alibaba open program. Evaluations demonstrate that our hybrid approach boosts the holistic QoS by 63.9% compared with the state-of-the-art peer algorithms.

Accurate pedestrian trajectory prediction is critical for ensuring the safety of autonomous vehicles and advancing higher levels of driving automation. However, the complex interpersonal interactions and highly dynamic trajectory patterns in real-world scenarios pose significant challenges to achieving precise predictions. Recently, Transformers have shown remarkable success in pedestrian trajectory prediction, primarily due to their effective modeling of temporal and spatial dependencies via Multi-Head Self-Attention (MHA) mechanisms. Despite these advancements, existing self-attention methods often rely on Euclidean distance-based metrics and dot-product operations, which are inadequate for capturing interaction-induced trajectory curvatures. To address this limitation, we propose a novel hybrid Transformer architecture, FuseFormer, that incorporates Geodesic Self-Attention (GSA) mechanisms. GSA utilizes geodesic distances to characterize interaction features effectively, complementing MHA, which excels in capturing local features and maintaining temporal correlations. FuseFormer employs a gating network to adaptively combine GSA and MHA embeddings, leveraging their complementary strengths. Additionally, FuseFormer integrates a Transformer-based Neural Ordinary Differential Equation (ODE) decoder to model trajectory temporal dynamics. This design enables the generation of future trajectories that align closely with motion trends while adapting the network depth to input sequence lengths. Experimental results demonstrate that FuseFormer achieves state-of-the-art performance across widely used pedestrian trajectory prediction datasets, including ETH/UCY, SDD, and NBA. These results underscore the model’s effectiveness and generalization capability in capturing complex interaction patterns and handling diverse scenarios.

Although Federated Learning (FL) is good at collaborative learning among devices without compromising their data privacy, it suffers from the problem of large-scale deployment in Mobile Edge Computing (MEC) applications. This is mainly because the varying memory sizes of edge devices inevitably result in limited sizes of their hosting models. According to the Cannikin Law, when dealing with heterogeneous devices with different memory sizes, the learning capability of existing homogeneous FL schemes is greatly restricted by the weakest device. Worse still, although existing heterogeneous FL methods enable a MEC application to involve numerous devices equipped with heterogeneous models, their knowledge aggregation processes require either extra training data or architecture similarity of models. To address the above issues, this paper presents a novel FL method named FedGraft that enables effective knowledge sharing among heterogeneous device models of different sizes without imposing unrealistic assumptions. In FedGraft, all the device models are grafted to a common rootstock based on our proposed model partitioning and grafting mechanism, facilitating knowledge sharing among heterogeneous models on top of a tree-like global model. Meanwhile, using our proposed device selection strategy, the reassembled submodels extracted from the global model can be reasonably dispatched to corresponding devices with sufficient memory, thus enhancing the overall FL performance. Comprehensive experimental results show that, compared with state-of-the-art heterogeneous FL methods, FedGraft can improve inference accuracy by up to 17% in various memory-constrained scenarios.

This work investigates the problem of efficiently learning discriminative low-dimensional (LD) representations of multiclass image objects. We propose a generic end-to-end approach that jointly optimizes sparse dictionary and convolutions for learning LOW-dimensional discriminative image representations, named SparConvLow, taking advantage of convolutional neural networks (CNNs), dictionary learning, and orthogonal projections. The whole learning process can be summarized as follows. First, a CNN module is employed to extract high-dimensional (HD) preliminary convolutional features. Second, to avoid the high computational cost of direct sparse coding on HD CNN features, we learn sparse representation (SR) over a task-driven dictionary in the space with the feature being orthogonally projected. We then exploit the discriminative projection on SR. The whole learning process is consistently treated as an end-to-end joint optimization problem of trace quotient maximization. The cost function is well-defined on the product of the CNN parameters space, the Stiefel manifold, the Oblique manifold, and the Grassmann manifold. By using the explicit gradient delivery, the cost function is optimized via a geometrical stochastic gradient descent (SGD) algorithm along with the chain rule and the backpropagation. The experimental results show that the proposed method can achieve a highly competitive performance with the state-of-the-art (SOTA) image classification, object categorization, and face recognition methods, under both supervised and semi-supervised settings. The code is available at https://github.com/MVPR-Group/SparConvLow.

5G mobile communication techniques are widely applied in ubiquitous communication scenarios (e.g., smart navigation and smart transportation), which require time synchronization among mobile devices. However, the built-in time synchronization software of Android phones presents large time offsets with hundreds of milliseconds (ms), and the mainstream time synchronization techniques have specific limitations: 1) the Network Time Protocol (NTP) has too large offset to meet the real-time information interaction among mobile devices; 2) the Linux Precision Time Protocol (LinuxPTP) exists hardware dependence and cannot be implemented on Android and 5G networks; and 3) the Global Navigation Satellite System (GNSS) requires installing a hardware receiver on each mobile device. In this study, we develop a Mobile Precision Time Protocol (MobiPTP), which is hardware-independent and compatible with various network types, including Wide-Area Network (WAN), Local-Area Network (LAN), wired and wireless networks. The main challenges include signal strength instability and uplink-downlink asymmetry. We propose a dynamic time synchronization algorithm and an asymmetry compensation strategy to overcome these challenges. Regardless of high-speed mobile or crowded conditions in 5G networks, MobiPTP demonstrates an average offset of 9 ms, outperforming the NTP-based open-source software Chrony (about 30 ms). MobiPTP has been successfully deployed in multiple real-world ubiquitous communication scenarios and always demonstrates much lower offsets than Chrony.

Function offloading problems play a crucial role in optimizing the performance of applications in serverless edge computing (SEC). Existing research has extensively explored function offloading strategies based on optimizing a single objective. However, a significant challenge arises when users expect to optimize multiple objectives according to the relative importance of these objectives. This challenge becomes particularly pronounced when the relative importance of the objectives dynamically shifts. Consequently, there is an urgent need for research into multi-objective function offloading methods. In this paper, we redefine the SEC function offloading problem as a dynamic multi-objective optimization issue and propose a novel approach based on Multi-objective Reinforcement Learning (MORL) called MOSEC. MOSEC can coordinately optimize three objectives, i.e., application completion time, User Device (UD) energy consumption, and user cost. To reduce the impact of extrapolation errors, MOSEC integrates a Near-on Experience Replay (NER) strategy during the model training. Furthermore, MOSEC adopts our proposed Earliest First (EF) scheme to maintain the policies learned previously, which can efficiently mitigate the catastrophic policy forgetting problem. Extensive experiments conducted on various generated applications demonstrate the superiority of MOSEC over state-of-the-art multi-objective optimization algorithms.

With the rapid development of IoT technology, IoT-enabled systems, represented by smart homes, are becoming ubiquitous. In order to support personalized user requirements, such systems appeal to the end-user programming paradigm. This paradigm allows end-users to describe their requirements using TAP (Trigger-Action Programming) rules, which can be deployed on demand. However, writing TAP rules is error-prone and end-users are often unaware of the actual effects of the rules they write, given the context-sensitive nature of these effects. It is highly desirable that TAP rules can be validated before deployment. Unfortunately, requirements validation for IoT end-user programming has not received much attention so far. Therefore, this paper proposes to generate experience prototypes for IoT end-user programming using TAP rules. The difficulty lies in how to orchestrate user experience delivery service scenarios according to TAP rule and context changes, and effectively demonstrate these scenarios. We present a dynamic assembly approach for simulation model systems used for service scenario orchestration. By simulation, we synthesize desired system behaviors, system device behaviors, and context changes. Leveraging the simulation traces of each component, we employ animation techniques specifically designed to highlight user-aware changes. These experience prototypes allow end-users to directly understand the effects of the IoT-enabled systems, thereby determining whether their intentions are satisfied. Experimental results show that our approach is usable and effective for end-users and the generated experience prototypes are context-aware, capable of representing real-world service scenarios, effective, and efficient in requirements validation.

Since Industry 5.0 emphasizes that manufacturing enterprises should raise awareness of social contribution to achieve sustainable development, more and more meta-heuristic algorithms are investigated to save energy in manufacturing systems. Although non-dominated sorting-based meta-heuristics have been recognized as promising multi-objective optimization methods for solving the energy-efficient flexible job shop scheduling problem (EFJSP), it is hard to guarantee the quality of the Pareto front (e.g., total energy consumption, makespan) due to the lack of population diversity. This is mainly because an improper individual comparison inevitably reduces population diversity, thus limiting exploration and exploitation abilities during population updates. To achieve efficient population evolution, this paper introduces a novel space-cooperation multi-objective optimization (SCMO) method that can effectively solve EFJSP to obtain scheduling schemes with better trade-offs. By cooperatively evaluating the similarity among individuals in both the decision space and objective space, we propose a space-cooperation population update method based on a three-vector representation that can accurately eliminate repetitive individuals to derive higher-quality Pareto solutions. To further improve search efficiency, we propose a difference-driven local search, which selectively changes the positions of operations with higher differences to search for neighbors effectively. Based on the Taguchi method, we conduct experiments to obtain a suitable parameter combination of SCMO. Comprehensive experimental results show that, compared to state-of-the-art methods, our SCMO method achieves the highest HV and NR and the lowest IGD, with an average of 0.990, 0.952, and 0.001, respectively. Meanwhile, compared to traditional local search approaches, our difference-driven local search obtains twice the HV on instance Mk12 and reduces the solving time from 1521 s to 475 s.

Although Federated Learning (FL) enables collaborative model training without sharing the raw data of clients, it encounters low-performance problems caused by various heterogeneous scenarios. Due to the limitation of dispatching the same global model to clients for local training, traditional Federated Average (FedAvg)-based FL models face the problem of easily getting stuck into a sharp solution, which results in training a low-performance global model. To address this problem, this paper presents a novel FL approach named FedMut, which mutates the global model according to the gradient change to generate several intermediate models for the next round of training. Each intermediate model will be dispatched to a client for local training. Eventually, the global model converges into a flat area within the range of mutated models and has a well-generalization compared with the global model trained by FedAvg. Experimental results on well-known datasets demonstrate the effectiveness of our FedMut approach in various data heterogeneity scenarios.

Learning to collaborate has witnessed significant progress in multi-agent reinforcement learning (MARL). However, promoting coordination among agents and enhancing exploration capabilities remain challenges. In multi-agent environments, interactions between agents are limited in specific situations. Effective collaboration between agents thus requires a nuanced understanding of when and how agents' actions influence others.To this end, in this paper, we propose a novel MARL algorithm named Situation-Dependent Causal Influence-Based Cooperative Multi-agent Reinforcement Learning (SCIC), which incorporates a novel Intrinsic reward mechanism based on a new cooperation criterion measured by situation-dependent causal influence among agents.Our approach aims to detect inter-agent causal influences in specific situations based on the criterion using causal intervention and conditional mutual information. This effectively assists agents in exploring states that can positively impact other agents, thus promoting cooperation between agents.The resulting update links coordinated exploration and intrinsic reward distribution, which enhance overall collaboration and performance.Experimental results on various MARL benchmarks demonstrate the superiority of our method compared to state-of-the-art approaches.

Diffusion generative models (DMs) have achieved promising results in image and graph generation. However, real-world graphs, such as social networks, molecular graphs, and traffic graphs, generally share non-Euclidean topologies and hidden hierarchies. For example, the degree distributions of graphs are mostly power-law distributions. The current latent diffusion model embeds the hierarchical data in a Euclidean space, which leads to distortions and interferes with modeling the distribution. Instead, hyperbolic space has been found to be more suitable for capturing complex hierarchical structures due to its exponential growth property. In order to simultaneously utilize the data generation capabilities of diffusion models and the ability of hyperbolic embeddings to extract latent hierarchical distributions, we propose a novel graph generation method called, Hyperbolic Graph Diffusion Model (HGDM), which consists of an auto-encoder to encode nodes into successive hyperbolic embeddings, and a DM that operates in the hyperbolic latent space. HGDM captures the crucial graph structure distributions by constructing a hyperbolic potential node space that incorporates edge information. Extensive experiments show that HGDM achieves better performance in generic graph and molecule generation benchmarks, with a 48% improvement in the quality of graph generation with highly hierarchical structures.

Few-shot image generation, as an important yet challenging visual task, still suffers from the trade-off between generation quality and diversity. According to the principle of feature-matching learning, existing fusion-based methods usually fuse different features by using similarity measurements or attention mechanisms, which may match features inaccurately and lead to artifacts in the texture and structure of generated images. In this paper, we propose an exact Fusion via Feature Distribution matching Generative Adversarial Network (F2DGAN) for few-shot image generation. The rationale behind this is that feature distribution matching is much more reliable than feature matching to explore the statistical characters in image feature space for limited real-world data. To model feature distributions from only a few examples for feature fusion, we design a novel variational feature distribution matching fusion module to perform exact fusion by empirical cumulative distribution functions. Specifically, we employ a variational autoencoder to transform deep image features into distributions and fuse different features exactly by applying histogram matching. Additionally, we formulate two effective losses to guide the matching process for better fitting our fusion strategy. Extensive experiments compared with state-of-the-art methods on three public datasets demonstrate the superiority of F2DGAN for few-shot image generation in terms of generation quality and diversity, and the effectiveness of data augmentation in downstream classification tasks11Code is available at: https:/github.com/ZYBOBO/F2DGAN.

Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e.g., computing capacity, memory size) of devices and uncertain operating environments. To address these issues, this paper introduces an effective FL approach named AdaptiveFL based on a novel fine-grained width-wise model pruning mechanism, which can generate various heterogeneous local models for heterogeneous AIoT devices. By using our proposed reinforcement learning-based device selection strategy, AdaptiveFL can adaptively dispatch suitable heterogeneous models to corresponding AIoT devices based on their available resources for local training. Experimental results show that, compared to state-of-the-art methods, AdaptiveFL can achieve up to 8.94% inference improvements for both IID and non-IID scenarios.

Human trajectory prediction is crucial in human-computer interaction and even in the safety of autonomous driving. In this work, A new method, called Social Latent Ordinary Differential Equation (Social LODE), is introduced for predicting human trajectories. The backbone of Social LODE consists of a conditional Variational Autoencoder (VAE) architecture based on Recurrent Neural Network (RNN). The hidden state updated by RNN is often discrete, but the human trajectory is continuous and uncertain. Thus, we use Latent ODEs as the decoder of VAE to overcome the limitation of RNN. Finally, we demonstrate that Social LODE achieves state-of-the-art compared to other methods, such as those involving the ETH/UCY and SDD datasets.

As a promising distributed machine learning paradigm, Federated Learning (FL) has attracted increasing attention to deal with data silo problems without compromising user privacy. By adopting the classic one-to-multi training scheme (i.e., FedAvg), where the cloud server dispatches one single global model to multiple involved clients, conventional FL methods can achieve collaborative model training without data sharing. However, since only one global model cannot always accommodate all the incompatible convergence directions of local models, existing FL approaches greatly suffer from inferior classification accuracy. To address this issue, we present an efficient FL framework named FedCross, which uses a novel multi-to-multi FL training scheme based on our proposed multi-model cross-aggregation approach. Unlike traditional FL methods, in each round of FL training, FedCross uses multiple middleware models to conduct weighted fusion individually. Since the middleware models used by FedCross can quickly converge into the same flat valley in terms of loss landscapes, the generated global model can achieve a well-generalization. Experimental results on various well-known datasets show that, compared with state-of-the-art FL methods, Fed Cross can significantly improve FL accuracy within both IID and non-IID scenarios without causing additional communication overhead.

In many real-world applications such as social network analysis and online marketing/advertising, community detection is a fundamental task to identify communities (subgraphs) in social networks with high structural cohesiveness. While previous works focus on detecting communities alone, they do not consider the collective influences of users in these communities on other user nodes in social networks. Inspired by this, in this paper, we investigate the influence propagation from some seed communities and their influential effects that result in the influenced communities. We propose a novel problem, named Top-L most Influential Community DEtection ($\text{Top}L$-ICDE) over social networks, which aims to retrieve top-$L$seed communities with the highest influences, having high structural cohesiveness, and containing user-specified query keywords. To efficiently tackle the$\text{Top}L$-ICDE problem, we design effective pruning strategies to filter out false alarms of seed communities and propose an effective index mechanism to facilitate efficient Top-$L$community retrieval. We develop an efficient$\text{Top}L$-ICDE answering algorithm by traversing the index and applying our proposed pruning strategies. We also formulate and tackle a variant of$\text{Top}L$-ICDE, named diversified top-L most influential community detection ($\text{Top}L$-ICDE), which returns a set of$L$diversified communities with the highest diversity score (i.e., collaborative influences by$L$communities). We prove that$\text{DTop}L$-ICDE is NP-hard, and propose an efficient greedy algorithm with our designed diversity score pruning. Through extensive experiments, we verify the efficiency and effectiveness of our proposed$\text{Top}L$-ICDE and$\text{DTop}L$-ICDE approaches over real/synthetic social networks under various parameter settings.

With the rapid development of autonomous driving systems, 3D object detection based on Bird’s Eye View (BEV) in road scenes has witnessed great progress over the past few years. As a road scene exhibits a part-whole hierarchy between the within objects and the scene itself, simple parts (e.g., roads, lane lines, vehicles and pedestrians) can be assembled into progressively more complex shapes to form a BEV representation of the whole road scene. Therefore, a BEV often has multiple levels of freedom on motion, i.e., the rotation and the moving shift of the whole BEV, and the random movements of objects (e.g., pedestrians and vehicles) inside the BEV. However, most of the current single-sensor or multi-sensor fusion-based BEV object detection methods have not yet taken into account capturing such multi-level motion in a BEV. To address this problem, we propose a product group equivariant object detection network framework that is equivariant with respect to multiple levels of symmetry groups based on multi-sensor fusion. The proposed framework extracts local equivariant features of objects in point clouds, while global equivariant features are extracted in both point clouds and images. Furthermore, the network learns diverse rotation-equivariant features and mitigates a significant amount of detection errors caused by rotations of BEV and objects inside a BEV, thereby further enhancing the performance of object detection. The experiment results show that the network architecture significantly improves object detection on mAP and NDS, respectively. In addition, in order to demonstrate the effectiveness of the proposed local-multi-global equivariant components, we conduct sufficient ablation experiments. The results show that the individual components are indispensable for the object detection performance improvement of the overall network architecture.

As an irregular and sparse form of data, 3D point cloud data is widely used in the fields of computer vision and machine learning. Its effective classification and recognition are of great significance. In many cases, task data does not arrive all at once but is acquired in batches over time. However, in deep learning, continual learning faces the problem of catastrophic forgetting, where the model loses memory of old tasks while learning new ones. How to retain old knowledge while learning new knowledge is a significant challenge. To address these challenges, existing replay-based strategies alleviate this issue by storing small portions of old samples. However, this often leads to an imbalance between new and old data, affecting performance. Additionally, point cloud data typically has complex non-Euclidean structures, with potential hierarchical relationships within and between point cloud objects. Current deep learning models based on Euclidean space struggle to capture the hierarchical prior features of point clouds. Therefore, in this paper, we introduce a continual learning method based on a replay mechanism and explore how to incorporate hyperbolic space into continual learning tasks to enhance feature representation capabilities. We propose a manifold replay strategy in hyperbolic space, termed HyMR. Specifically, this paper presents a knowledge distillation strategy that combines global and local information, and utilizes manifold spherical projection to select representative old data for replay. Experiments demonstrate that this method achieves good results in continual learning tasks on point cloud datasets such as ShapeNet and ModelNet.

Traffic flow prediction is crucial for intelligent transportation systems (ITS). Traditional graph convolutional networks (GCNs) have limitations in handling road network data. These GCNs can only handle binary relationships between nodes and cannot effectively capture the dynamic and nonlinear spatial dependencies among multiple nodes in the road network. This paper proposes an innovative spatial-temporal traffic flow prediction model to address this challenge. Firstly, by introducing novel graphs fusion and hypergraph encoding module, a fused graph and its dual hypergraph are constructed to provide richer structural information for the model. Then, the model can learn complex relationships among multiple nodes through the collaborative convolution of GCN and hypergraph convolutional network (HGCN). To comprehensively capture the dynamic nature of traffic flow, we utilize a variant of Transformer combined with time encoding information to capture the periodicity in the data, thereby enhancing the model’s ability to recognize periodic traffic flow patterns. Comprehensive experimental results on two publicly accessible real-world traffic datasets demonstrate the superiority of our proposed model over state-of-the-art traffic prediction models.

Vehicle re-identification (re-ID) has attracted significant attention within the computer vision community due to its wide-ranging applications in intelligent transportation systems and law enforcement. Nevertheless, this field faces considerable challenges owing to the high inter-class similarity and the large intra-class difference among vehicles. To address these challenges, this paper proposes a novel network incorporating a dual self-attention mechanism based on a space-channel grouped compression operation (DSA-SCGC). This innovative approach combines channel and spatial self-attention mechanisms to selectively enhance pivotal channel features and spatial local details while minimizing attention toward backgrounds and occlusions commonly encountered in real-world scenarios. Moreover, to address the issue of spatial information loss in channel attention, we propose a space-channel grouped compression (SCGC) operation that effectively compresses spatial information into channels, thereby significantly preserving spatial information. Comprehensive experiments conducted on the VeRi-776 and VehicleID datasets validate the superiority of our proposed DSA-SCGC model over the existing state-of-the-art vehicle re-identification methods.

Although Federated Learning (FL) enables global model training across clients without compromising their raw data, due to the un- evenly distributed data among clients, existing Federated Averaging (FedAvg)-based methods suffer from the problem of low inference performance. Specifically, different data distributions among clients lead to various optimization directions of local models. Aggregat- ing local models usually results in a low-generalized global model, which performs worse on most of the clients. To address the above issue, inspired by the observation from a geometric perspective that a well-generalized solution is located in a flat area rather than a sharp area, we propose a novel and heuristic FL paradigm named FedMR (Federated Model Recombination). The goal of FedMR is to guide the recombined models to be trained towards a flat area. Unlike conventional FedAvg-based methods, in FedMR, the cloud server recombines collected local models by shuffling each layer of them to generate multiple recombined models for local training on clients rather than an aggregated global model. Since the area of the flat area is larger than the sharp area, when local models are located in different areas, recombined models have a higher probability of locating in a flat area. When all recombined models are located in the same flat area, they are optimized towards the same direction. We theoretically analyze the convergence of model recombination. Experimental results show that, compared with state-of-the-art FL methods, FedMR can significantly improve the inference accuracy without exposing the privacy of each client.

Large-scale streaming matrix multiplication is very common in various applications, sparking significant interest in develop efficient algorithms for approximate matrix multiplication (AMM) over streams. In addition, many practical scenarios require to process time-sensitive data and aim to compute matrix multiplication for most recent columns of the data matrices rather than the entire matrices, which motivated us to study efficient AMM algorithms over sliding windows. In this paper, we present two novel deterministic algorithms for this problem and provide corresponding error guarantees. We further reduce the space and time costs of our methods for sparse matrices by performing an approximate singular value decomposition which can utilize the sparsity of matrices. Extensive experimental results on both synthetic and real-world datasets validate our theoretical analysis and highlight the efficiency of our methods.

Due to the increasing popularity of Artificial Intelligence (AI), more and more backdoor attacks are designed to mislead Deep Neural Network (DNN) predictions by manipulating training samples or processes. Although backdoor attacks have been investigated in various scenarios, they still suffer from the problems of both low fidelity of poisoned samples and non-negligible transfer in latent space, which make them easily identified by existing backdoor detection algorithms. To overcome this weakness, this paper proposes a novel frequency-based backdoor attack method named WaveAttack, which obtains high-frequency image features through Discrete Wavelet Transform (DWT) to generate highly stealthy backdoor triggers. By introducing an asymmetric frequency obfuscation method, our approach adds an adaptive residual to the training and inference stages to improve the impact of triggers, thus further enhancing the effectiveness of WaveAttack. Comprehensive experimental results show that, WaveAttack can not only achieve higher effectiveness than state-of-the-art backdoor attack methods, but also outperform them in the fidelity of images (i.e., by up to 28.27\% improvement in PSNR, 1.61\% improvement in SSIM, and 70.59\% reduction in IS). Our code is available at https://github.com/BililiCode/WaveAttack.

The advancement of Machine Learning has enabled the widespread deployment of Machine Learning as a Service (MLaaS) applications. However, the untrustworthy nature of third-party ML services poses backdoor threats. Existing defenses in MLaaS are limited by their reliance on training samples or white-box model analysis, highlighting the need for a black-box backdoor purification method. In our paper, we attempt to use diffusion models for purification by introducing noise in a forward diffusion process to destroy backdoors and recover clean samples through a reverse generative process. However, since a higher noise also destroys the semantics of the original samples, it still results in a low restoration performance. To investigate the effectiveness of noise in eliminating different types of backdoors, we conducted a preliminary study, which demonstrates that backdoors with low visibility can be easily destroyed by lightweight noise and those with high visibility need to be destroyed by high noise but can be easily detected. Based on the study, we propose SampDetox, which strategically combines lightweight and high noise. SampDetox applies weak noise to eliminate low-visibility backdoors and compares the structural similarity between the recovered and original samples to localize high-visibility backdoors. Intensive noise is then applied to these localized areas, destroying the high-visibility backdoors while preserving global semantic information. As a result, detoxified samples can be used for inference, even by poisoned models. Comprehensive experiments demonstrate the effectiveness of SampDetox in defending against various state-of-the-art backdoor attacks.

Due to the advantages of privacy-preserving, Federated Learning (FL) is widely used in distributed machine learning systems.However, existing FL methods suffer from lowinference performance caused by data heterogeneity.Specifically, due to heterogeneous data, the optimization directions of different local models vary greatly, making it difficult for the traditional FL method to get a generalized global model that performs well on all clients.As one of the state-of-the-art FL methods, the mutation-based FL method attempts to adopt a stochastic mutation strategy to guide the model training towards a wellgeneralized area (i.e., flat area in the loss landscape).Specifically, mutation allows the model to shift within the solution space, providing an opportunity to escape areas with poor generalization (i.e., sharp area).However, the stochastic mutation strategy easily results in diverse optimal directions of mutated models, which limits the performance of the existing mutation-based FL method.To achieve higher performance, this paper proposes a novel mutation-based FL approach named FedQP, utilizing a quadratic programming strategy to regulate the mutation directions wisely.By biasing the model mutation towards the direction of gradient update rather than traditional random mutation, FedQP can effectively guide the model to optimize towards a well-generalized area (i.e., flat area).Experiments on multiple well-known datasets show that our quadratic programming-guided mutation strategy effectively improves the inference accuracy of the global model in various heterogeneous data scenarios.

The classic problem of exact subgraph matching returns those subgraphs in a large-scale data graph that are isomorphic to a given query graph, which has gained increasing importance in many real-world applications such as social network analysis, knowledge graph discovery in the Semantic Web, bibliographical network mining, and so on. In this paper, we propose a novel and effective graph neural network (GNN)-based path embedding framework (GNN-PE), which allows efficient exact subgraph matching without introducing false dismissals. Unlike traditional GNN-based graph embeddings that only produce approximate subgraph matching results, in this paper, we carefully devise GNN-based embeddings for paths, such that: if two paths (and 1-hop neighbors of vertices on them) have the subgraph relationship, their corresponding GNN-based embedding vectors will strictly follow the dominance relationship. With such a newly designed property of path dominance embeddings, we are able to propose effective pruning strategies based on path label/dominance embeddings and guarantee no false dismissals for subgraph matching. We build multidimensional indexes over path embedding vectors, and develop an efficient subgraph matching algorithm by traversing indexes over graph partitions in parallel and applying our pruning methods. We also propose a cost-model-based query plan that obtains query paths from the query graph with low query cost. Through extensive experiments, we confirm the efficiency and effectiveness of our proposed GNN-PE approach for exact subgraph matching on both real and synthetic graph data.

Along with the increasing popularity of deep learning (DL) techniques, more and more Artificial Intelligence of Things (AIoT) systems are adopting federated learning (FL) to enable privacy-aware collaborative learning among the AIoT devices. However, due to the inherent data and device heterogeneity issues, the existing FL-based AIoT systems suffer from the model selection problem. Although various heterogeneous FL methods have been investigated to enable collaborative training among the heterogeneous models, there is still a lack of 1) wise heterogeneous model generation methods for the devices; 2) consideration of uncertain factors; and 3) performance guarantee for the large models, thus strongly limiting the overall FL performance. To address the above issues, this article introduces a novel heterogeneous FL framework named FlexFL. By adopting our average percentage of zeros (APoZ)-guided flexible pruning strategy, FlexFL can effectively derive best-fit models for the heterogeneous devices to explore their greatest potential. Meanwhile, our proposed adaptive local pruning strategy allows the AIoT devices to prune their received models according to their varying resources within uncertain scenarios. Moreover, based on the self-knowledge distillation, FlexFL can enhance the inference performance of the large models by learning the knowledge from the small models. Comprehensive experimental results show that, compared to the state-of-the-art heterogeneous FL methods, FlexFL can significantly improve the overall inference accuracy by up to 14.24%. Our code can be found herehttps://github.com/mastlab-T3S/FlexFL.

Federated learning (FL) as a promising distributed machine learning paradigm has been widely adopted in Artificial Intelligence of Things (AIoT) applications. However, the efficiency and inference capability of FL is seriously limited due to the presence of stragglers and data imbalance across massive AIoT devices, respectively. To address the above challenges, we present a novel asynchronous FL approach named CaBaFL, which includes a hierarchical cache-based aggregation mechanism and a feature balance-guided device selection strategy. CaBaFL maintains multiple intermediate models simultaneously for local training. The hierarchical cache-based aggregation mechanism enables each intermediate model to be trained on multiple devices to align the training time and mitigate the straggler issue. In specific, each intermediate model is stored in a low-level cache for local training and when it is trained by sufficient local devices, it will be stored in a high-level cache for aggregation. To address the problem of imbalanced data, the feature balance-guided device selection strategy in CaBaFL adopts the activation distribution as a metric, which enables each intermediate model to be trained across devices with totally balanced data distributions before aggregation. Experimental results show that compared to the state-of-the-art FL methods, CaBaFL achieves up to 9.26X training acceleration and 19.71% accuracy improvements.

The tremendous expansion of edge data traffic poses great challenges to network bandwidth and service responsiveness for mobile computing. Edge caching has emerged as a promising method to alleviate these issues by storing a portion of data at the network edge. However, existing caching approaches suffer from either poor caching efficiency with low content-hit ratio or unintelligence of caching policies lacking self-adjustability. In this paper, we propose ICE, a novel Intelligent Edge Caching scheme using a deep reinforcement learning (DRL) method to capture specific valuable information from the requested data. With the benefit of our proposed popularity model based on Newton's law of cooling, ICE fully takes into account the popularity of the contents to be cached and leverages the formulated Markov decision model to decide whether or not the contents should be cached. Moreover, to further improve the caching efficiency, we propose a novel distributed multi-node caching framework, named DCCC, assisted by a multi-tiered caching hierarchy. Comprehensive experiments show that the single-node ICE scheme greatly improves the cache hit rate and contents exchanging time in comparison with both DRL-based and legacy approaches, and our distributed multi-node caching scheme DCCC further significantly improves the overall utilization of caching space.

The network system deployed in hazardous environments is a key component of hazard-aware cyber-physical systems (CPSs) and its performance highly depends on surrounding environments. Due to the mobility of network nodes (e.g., portable IoT devices), frequently changeable network topology and links, as well as other external interferences such as electromagnetic interference, ensuring adaptivity and reliability of hazard-aware CPSs is of utmost importance. Meanwhile, the timeliness of message transmission is stringent in hazardous environments because the violation of timing requirements may lead to serious consequences. Last but not least, portable IoT devices are typically energy limited, thus ensuring a sustainable message transmission is highly necessary. In this paper, we aim at optimizing the reliability of hazard-aware CPSs while meeting the timing and energy constraints. To this end, we develop the first hazard-aware CPS model and study the impacts of surrounding environments (i.e., physical side) to the network infrastructure of a hazard-aware CPS (i.e., cyber side) with respect to reliability. We also propose a new scheme that adaptively tunes the fault tolerance strategies and admission strategies for real-time messages, to increase the reliability of hazard-aware CPSs under the energy constraint. Extensive simulation results demonstrate that our proposed scheme is capable of increasing system reliability by up to 4.21× with a lower deadline miss rate and runtime overhead compared with the state-of-the-art approaches.

Due to their fast speed and easy deployment, Unmanned Aerial Vehicles (UAVs) have been widely used across various sectors, such as earthquake rescue, medical assistance, and smart agriculture. However, UAVs in delivery networks face significant challenges due to limited battery life and computational capabilities, particularly for tasks that entail intensive computing workflows. In this context, Multi-access Edge Computing (MEC), which provides computing resources in close proximity to mobile terminal devices, has emerged as a promising solution. UAVs can offload computing tasks to MEC resources across diverse Internet of Things (IoT) environments. Although task offloading can enhance their task processing capability, it simultaneously brings additional costs, encompassing data transmission time and energy consumption. To address these issues, this paper proposes a novel workflow scheduling method based on the Proximal Policy Optimization (PPO) algorithm, aimed at optimizing UAV energy consumption within MEC environments. The proposed approach establishes a learning-based workflow scheduling strategy harnessing the adaptability of the PPO algorithm to manage dynamic and intricate scenarios, which facilitates efficient task allocation to optimal computational resources while accounting for flight time constraints. Extensive experiments conducted on various well-known scientific workflow benchmarks in real-world UAV delivery networks validate the effectiveness of our method. Compared with state-of-the-art methods, our approach significantly reduces UAV energy consumption and task completion time, simultaneously increasing UAV’s effective payload capacity.

Due to repetitive trial-and-error style interactions between agents and a fixed traffic environment during the policy learning, existing Reinforcement Learning (RL)-based Traffic Signal Control (TSC) methods greatly suffer from long RL training time and poor adaptability of RL agents to other complex traffic environments. To address these problems, we propose a novel Adversarial Inverse Reinforcement Learning (AIRL)-based pre-training method named InitLight, which enables effective initial model generation for TSC agents. Unlike traditional RL-based TSC approaches that train a large number of agents simultaneously for a specific multi-intersection environment, InitLight pre-trains only one single initial model based on multiple single-intersection environments together with their expert trajectories. Since the reward function learned by InitLight can recover ground-truth TSC rewards for different intersections at optimality, the pre-trained agent can be deployed at intersections of any traffic environments as initial models to accelerate subsequent overall global RL training. Comprehensive experimental results show that, the initial model generated by InitLight can not only significantly accelerate the convergence with much fewer episodes, but also own superior generalization ability to accommodate various kinds of complex traffic environments.

In this paper, we focus on vehicle detection algorithms from UAV images in intelligent transportation applications. We propose an improved YOLOX model called CCHYOLOX for the problems of dense distribution and drastic scale changes of vehicle targets from the UAV viewpoint. Firstly, we construct a novel plug-and-play module, called Correlation Extraction and Feature Fusion (CEFF), to process the multi-layer adaptive fusion of pyramidal features. It enables the adaptive fusion of features in adjacent layers by adding spatial-awareness and extracting global channels correlation of adjacent layers features to mitigate the effect of target size diversity. Then, we design a special cascade strategy, including a feature alignment module named DConv, for single-stage and anchor-free detectors by considering the feature offset problem to produce more accurate detection bounding boxes. The cascade strategy allows the model to improve performance with little increase in computational cost. Finally, a high-resolution branch is designed for the small-target detection task, which greatly improves the detection accuracy of the model. Experiments on the challenging Visdrone-vehicle and Drone Vehicle datasets show that the proposed method effectively tackle the detection accuracy decrease caused by the above problems. CCH-YOLOX achieves 43.2% mAP and 57.3% mAP on the above two datasets, respectively, which is about 3%-4% higher than the strong baseline model (YOLOX) and exceeds many current popular models. The code is available at https://github.com/lz06787/CCH-YOLOX

Patient similarity assessment (PSA) is pivotal to evidence-based and personalized medicine, enabled by analyzing the increasingly available electronic health records (EHRs). However, machine learning approaches for PSA have to deal with inherent data deficiencies of EHRs, namely missing values, noise, and small sample sizes. In this work, an end-to-end discriminative learning framework, called SparGE, is proposed to address these data challenges of EHR for PSA. SparGE measures similarity by jointly sparse coding and graph embedding. First, we use low-rank constrained sparse coding to identify and calculate weight for similar patients, while denoising against missing values. Then, graph embedding on sparse representations is adopted to measure the similarity between patient pairs via preserving local relationships defined by distances. Finally, a global cost function is constructed to optimize related parameters. Experimental results on two private and public real-world healthcare datasets, namely SingHEART and MIMIC-III, show that the proposed SparGE significantly outperforms other machine learning patient similarity methods.

Due to the popularity of Artificial Intelligence (AI) techniques, we are witnessing an increasing number of backdoor injection attacks that are designed to maliciously threaten Deep Neural Networks (DNNs) causing misclassification. Although there exist various defense methods that can effectively erase backdoors from DNNs, they greatly suffer from both high Attack Success Rate (ASR) and a non-negligible loss in Benign Accuracy (BA). Inspired by the observation that a backdoored DNN tends to form a new cluster in its feature spaces for poisoned data, in this paper, we propose a novel two-stage backdoor defense method, named MCLDef, based on Model-Contrastive Learning (MCL). MCLDef can purify the backdoored model by pulling the feature representations of poisoned data towards those of their clean data counterparts. Due to the shrunken cluster of poisoned data, the backdoor formed by end-to-end supervised learning can be effectively eliminated. Comprehensive experimental results show that, with only 5% of clean data, MCLDef significantly outperforms state-of-the-art defense methods by up to 95.79% reduction in ASR, while in most cases, the BA degradation can be controlled within less than 2%. Our code is available at https://github.com/Zhihao151/MCL.

As a promising distributed machine learning paradigm that enables collaborative training without compromising data privacy, Federated Learning (FL) has been increasingly used in large-scale A IoT (Artificial Intelligence of Things) system design. However, due to the lack of efficient management of straggling devices, existing FL methods greatly suffer from the problems of long response time (e.g., training and communication latency) and low inference accuracy. Things become even worse when taking various uncertain factors (e.g., network delays, performance variances caused by process variation) existing in AIoT scenarios into account. To address this issue, this paper proposes a novel asynchronous FL framework named GitFL, whose implementation is inspired by the famous version control system Git. Unlike traditional FL, the cloud server of GitFL maintains a master model (i.e., the global model) together with a set of branch models indicating the trained local models committed by selected devices, where the master model is updated based on both all the pushed branch models and their version information, and only the branch models after the pull operation are dispatched to devices. By using our proposed Reinforcement Learning (RL)-based device selection mechanism, a pulled branch model with an older version will be more likely to be dispatched to a faster and less frequently selected device for the next round of local training. In this way, GitFL enables both effective controls of model staleness and adaptive load balance of versioned models among straggling devices, thus avoiding performance deterioration while ensuring real-time performance. Comprehensive experimental results on well-known models and datasets show that, compared with state-of-the-art asynchronous and synchronous FL methods, GitFL can achieve up to 2.64X training acceleration and 7.88 % inference accuracy improvements in various uncertain scenarios.

As a standardized software framework and open E/E system architecture, the AUTomotive Open System ARchitecture (AUTOSAR) has been widely applied to autonomous driving systems to enable real-time control. However, due to the increasing design complexity and the lack of efficient algorithms and design automation tools, it is difficult to quickly figure out an optimal task scheduling scheme for an AUTOSAR-based system. To address this problem, we introduce a novel task scheduling method that can parallelly search for an optimal solution with the help of our proposed pruning strategy. Experimental results on a real-world AUTOSAR-based autonomous driving system demonstrate that our approach can achieve much better task scheduling solutions than the ones obtained manually and significantly reduce the overall task scheduling time.

Although Reinforcement Learning (RL)-based methods have been widely researched in Traffic Signal Control (TSC), they still suffer from the problems of poor adaptation to real-world traffic scenarios and slow convergence to optimized solutions. This is because RL-based TSC methods have a high dependency on accurate modeling of the environment. With transportation infrastructure constraints, some vehicle dynamic information in the road network is difficult to obtain in real-time, which strongly limits the capability of RL agents. To address this problem, we propose a novel real-time federated traffic signal control system named RTLight, which can efficiently control traffic lights in real-time for multi-intersection scenarios. Based on the digital twin, the RL agent can obtain sufficient traffic information and interact with the environment in real time. Inspired by federated learning, our system supports knowledge sharing among intersections, which improves the overall convergence rate and control performance. Note that, we have deployed our RTLight system for large-scale application validation in Xishan district, Wuxi, China. Experimental results obtained from various real-world traffic scenarios demonstrate that RTLight can significantly improve the control performance.

In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based methods use episodic memory to replay samples of previous tasks. However, in the process of knowledge integration when learning a new task, this strategy also suffers from catastrophic forgetting due to an imbalance between old and new knowledge. To address this problem, we propose a novel replay strategy called Manifold Expansion Replay (MaER). We argue that expanding the implicit manifold of the knowledge representation in the episodic memory helps to improve the robustness and expressiveness of the model. To this end, we propose a greedy strategy to keep increasing the diameter of the implicit manifold represented by the knowledge in the buffer during memory management. In addition, we introduce Wasserstein distance instead of cross entropy as distillation loss to preserve previous knowledge. With extensive experimental validation on MNIST, CIFAR10, CIFAR100, and TinyImageNet, we show that the proposed method significantly improves the accuracy in continual learning setup, outperforming the state of the arts.

As a promising distributed machine learning paradigm, federated learning (FL) trains a central model with decentralized data without compromising user privacy, which makes it widely used by Artificial Intelligence Internet of Things (AIoT) applications. However, the traditional FL suffers from model inaccuracy, since it trains local models only using hard labels of data while useful information of incorrect predictions with small probabilities is ignored. Although various solutions try to tackle the bottleneck of the traditional FL, most of them introduce significant communication overhead, making the deployment of large-scale AIoT devices a great challenge. To address the above problem, this article presents a novel distillation-based FL (DFL) method that enables efficient and accurate FL for AIoT applications. By using knowledge distillation (KD), in each round of FL training, our approach uploads both the soft targets and local model gradients to the cloud server for aggregation, where the aggregation results are then dispatched to AIoT devices for the next round of local training. During the DFL local training, in addition to hard labels, the model predictions approximate soft targets, which can improve model accuracy by leveraging the knowledge of soft targets. To further improve our DFL model performance, we design a dynamic adjustment strategy of loss function weights for tuning the ratio of KD and FL, which can maximize the synergy between soft targets and hard labels. Comprehensive experimental results on well-known benchmarks show that our approach can significantly improve the model accuracy of FL without introducing significant communication overhead.

Artificial intelligence-based cyber-physical systems (CPS) applications have been spread across various fields such as smart cities, medical services, and industrial controls. When CPS devices are connected to a cloud server, big data streams generated by CPS devices impose enormous bandwidth pressure and exert excessive compute loads to the cloud server. Due to unpredictable environments and uncertainty in reality, these issues are mainly attributed to a large amount of high noise data captured and uploaded by CPS devices. To overcome these issues, this paper proposes a cyber-physical-cloud based framework for distributed deep neural networks (DDNNs) to prevent high noise data from being uploaded to the cloud. The proposed framework features a lightweight data filtering module enabled by depthwise separable convolutions to identify and filter out the high noise data that the cloud cannot recognize. Extensive experimental results demonstrate that the proposed data filtering module can achieve an accuracy of up to 83.72% in identifying high noise data and the proposed framework can effectively save bandwidth of up to 63.42% as compared to benchmarking methods. Note to Practitioners—This paper is motivated by the problems of enormous bandwidth pressure and excessive cloud compute loads in cyber-physical-cloud distributed computing paradigms. These problems are mainly caused by high noise data generated by CPS devices, because CPS devices often work in disturbing and unstable environments and there are uncontrollable uncertainties in reality. Especially for the emerging artificial intelligence-driven cyber-physical-cloud distributed paradigms, there is no existing research to solve the unnecessary transmission and cloud compute loads caused by high noise data. To tackle the challenge, this paper develops a novel cyber-physical-cloud distributed framework with data filtering capabilities to prevent high noise data from being uploaded. The proposed framework supports two popular loosely coupled and closely coupled distributed computing paradigms. Extensive experiments confirm that the proposed cyber-physical-cloud distributed framework can efficiently filter out high noise data and alleviate unnecessary transmission and needless cloud compute loads introduced by high noise data.

The Clock Constraint Specification Language (CCSL) has been widely acknowledged as a promising system-level specification for the modeling and analysis of timing behaviors of real-time and embedded systems. However, along with the increasing complexity of modern systems coupled with strict time-to-market constraints, it becomes more and more difficult for requirement engineers to accurately figure out CCSL specifications from natural language-based requirement documents, since they lack both expertise in formal CCSL modeling and design automation tools to support quick and automatic generation of CCSL specifications. To solve the above problem, in this paper we introduce a novel and efficient Reinforcement Learning (RL)-based synthesis approach that can facilitate requirement engineers to quickly figure out their expected CCSL specifications. For a given incomplete CCSL specification, our approach adopts RL-based enumeration to explore all the feasible solutions to fill the holes within CCSL constraints, and leverages curiosity-driven exploration to accelerate the enumeration process. Based on the combination of our proposed curiosity-driven exploration heuristic and deductive reasoning techniques, our approach can not only prune unfruitful enumeration solutions effectively, but also optimize the enumeration process to search for the tightest solution quickly, thus the overall synthesis process can be accelerated dramatically. Comprehensive experimental results demonstrate that our approach significantly outperforms state-of-the-art methods in terms of both synthesis time and synthesis accuracy.

Convolutional neural networks (CNNs) have been widely adopted in many deep learning applications. However, training a deep CNN requests intensive data transfer, which is both time and energy consuming. Using resistive random-access memory (ReRAM) to process data locally in memory is an emerging solution to eliminate the massive data movement. However, training cannot be efficiently supported with current ReRAM-based PIM accelerators because of the frequent and high-cost ReRAM writing operations from the delay, energy, and ReRAM lifetime perspectives. In this paper, we observe that activation induced and weight updating induced writing operations dominate the training energy on ReRAM-based accelerators. We then exploit and leverage a new angle in intermediate data (e.g., activations and errors) sparsity that fits the unique computation pattern in ReRAM crossbars to effectively eliminate the insignificant ReRAM writings, thus, enabling highly efficient CNN training without hurting the training accuracy. The experiment results show our proposed scheme achieves averagely$4.97\times$($19.23\times$) energy saving and$1.38\times$($30.08\times$) speedup compared to the state-of-the-art ReRAM-based accelerator (GPU). Our scheme also achieves$4.55\times$lifetime enhancement compared to the state-of-the-art ReRAM accelerator.

Due to deeply intertwined physical and hardware/software components together with an increasing number of interconnected heterogeneous devices powered by artificial intelligence (AI) techniques, the design complexity of cyber–physical systems (CPSs) becomes skyrocketing. Model-driven engineering (MDE) methods have been proven to be effective in increasing the productivity of CPS design. However, there is still a lack of MDE approaches that enable design space exploration as well as the code generation for the design of Artificial Intelligence of Things (AIoT)-based CPSs. To mitigate the situation, this article presents a unified modeling language named AIoTML for AIoT-based CPSs, which enables the construction of AI-based components across different modeling levels for the purposes of intelligent sensing and control. By extending the constructs of state-of-the-art domain-specific language (DSL) ThingML, AIoTML can seamlessly unify the modeling of both autonomous executions of AIoT devices and their surrounding physical environment, which facilitates both platform-independent simulation and control optimization for platform-specific CPSs. The compiler developed for AIoTML provides a family of code generators to support the construction of digital twins on various heterogeneous target AIoT platforms. Comprehensive evaluations on two complex real-world designs demonstrate the effectiveness of our AIoTML approach in the fast development of AIoT-based CPSs with high control quality.

As a promising requirement-level specification language for timing behavior modeling, the clock constraint specification language (CCSL) has become popular in the model-driven design community for safety-critical embedded systems. However, due to the skyrocketing design complexity, in practice, it is hard for requirement engineers to accurately construct requirement models with expected timing behaviors using CCSL, especially, for safe timing behaviors. Although more and more CCSL synthesis approaches are designed to facilitate the generation of CCSL specifications, most of them cannot be used directly for the synthesis of requirements models. This is because existing CCSL synthesis methods: 1) focus on filling the holes of CCSL constraints rather than completing requirements models and 2) rely heavily on limited observations of system behaviors, while the (temporal) safety properties of target systems are neglected. To address these issues, this article proposes a novel method that enables the automated synthesis of safe timing behaviors for requirements models. By specifying the safety timing properties of target systems using safely-LTL, our approach adopts CCSL as an intermediate representation of requirement synthesis, where incomplete requirements models coupled with safely-LTL-based properties are encoded into CCSL constraints with holes. Guided by the samples (expected behaviors) provided by requirement engineers, our approach can automatically figure out the complete version of incomplete requirements models. Comprehensive experimental results on two complex case studies demonstrate that our approach can not only quickly and efficiently synthesize requirement models but also guarantee that the synthesized models satisfy specified safety properties in Safely-LTL form.

As a specific kind of cyber–physical systems (CPSs), autonomous robot clusters play an important role in various intelligent manufacturing fields. However, due to the increasing design complexity of robot clusters, it is becoming more and more challenging to guarantee the safety and efficiency for multirobot cooperative navigation in dynamic and complex environments. Although deep reinforcement learning (DRL) shows great potential in learning multirobot cooperative navigation policies, existing DRL-based approaches suffer from scalability issues and rarely consider the transferability of trained policies to new tasks. To address these problems, this article presents a novel DRL-based multirobot cooperative navigation approach named HRMR-Navi that equips each robot with both a two-layered hierarchical graph network model and an attention-based communication model. In our approach, the hierarchical graph network model can efficiently figure out hierarchical relations among all agents that either cooperate for efficiency or avoid obstacles for safety to derive more advanced strategies, and the communication model can accurately form a global view of the environment for a specific robot, thus, the multirobot cooperation efficiency can be further strengthened. Meanwhile, we propose an improved proximal policy optimization (PPO) algorithm based on the Maximum Entropy Reinforcement Learning, named MEPPO, to enhance the robot exploration ability. Comprehensive experimental results demonstrate that, compared with state-of-the-art approaches, HRMR-Navi can achieve more efficient cooperative navigation with less time cost, lower collision rate, higher scalability, and better knowledge transferability.

Although reinforcement learning (RL) approaches are promising in autonomous traffic signal control (TSC), they often suffer from the unfairness problem that causes extremely long waiting time at intersections for partial vehicles. This is mainly because the traditional RL methods focus on optimizing the overall traffic performance, while the fairness of individual vehicles is neglected. To address this problem, we propose a novel RL-based method named FairLight for the fair and efficient control of traffic with variable phase duration. Inspired by the concept of user satisfaction index (USI) proposed in the transportation field, we introduce a fairness index in the design of key RL elements, which specially considers the travel quality (e.g., fairness). Based on our proposed hierarchical action space method, FairLight can accurately allocate the duration of traffic lights for selected phases. Experimental results obtained from various well-known traffic benchmarks show that, compared with the state-of-the-art RL-based TSC methods, FairLight can not only achieve better fairness performance but also improve the control quality from the perspectives of the average travel time of vehicles and RL convergence speed.

Model checking is an automatic formal verification method that is widely applied to hardware verification. Safety properties are the mainly verified properties in practice that can be falsified within finite steps if they do not hold for systems. However, state-of-the-art safety model-checking algorithms cannot meet the performance requirement driven by the industry as the sizes of (hardware) systems to be verified increase rapidly. Therefore, more efficient techniques are still eagerly in demand. Recently, a new safety model-checking technique complementary approximate reachability (CAR) was presented and received considerable concerns from the community. CAR has shown its advantages in unsafe checking (bug finding), but cannot be as competitive as other state-of-the-art techniques, e.g., IC3/PDR, on safe checking (proving correctness). In this article, we propose four kinds of heuristics, two inspired by IC3/PDR and another two dedicated to CAR, to improve the performance of CAR. We integrate the heuristics into the open-source model checker SimpleCAR and compare the performance to the original CAR and IC3/PDR on 748 instances from the hardware model-checking competitions. Our results show that by fixing the time and memory resources, CAR can solve 124 more instances with the four proposed heuristics, i.e., 53.4% more instances can be solved comparing to the original CAR. Furthermore, CAR in both forward and backward directions can solve ten more instances than IC3/PDR in corresponding directions, and uniquely solve 44 more instances that IC3/PDR in corresponding directions cannot solve, which increases the capability of the current model-checking portfolio.

Due to the great advancement in computation, communication, and control technologies, the Internet of Things (IoT) can provide ubiquitous connectivity for anyone and anything at any time and any place, leading to a revolution in an information society. Protecting devices against various security threats is one of the most important challenges in IoT since IoT applications are generally security-critical systems while IoT devices are often poorly secured. For IoT devices, employing security services provided by smart gateways or edge/cloud servers to defend against various threats is an effective way to enhance their security. However, the finite battery energy of devices and the limited fund of device users hinder the wide application of security services in IoT. This necessitates the demand for designing new methodologies to tackle the tradeoff among security, energy, and fund of IoT devices. Therefore, this article attempts to optimize system security of IoT devices under energy and fund constraints. Specifically, to formulate the energy and fund constrained security optimization problem, we first propose a pricing model for the security services provided by the smart gateway. We then formulate the problem as a mixed-integer linear programming (MILP) problem. Since using a solver to address the MILP problem may be time consuming, we leverage the swarm intelligence technique to design a new task scheduling scheme that can efficiently solve the optimization problem. Extensive experiments are conducted to validate our proposed MILP and swarm intelligence-based task scheduling algorithms. Simulation results show that our scheme outperforms two state-of-the-art methods in improving system quality of security and guaranteeing schedule feasibility.

Due to the increasing complexity, the execution of workflow applications on cloud typically involves a large number of virtual machines (VMs), which makes the cost as well as energy consumption a great concern. To alleviate this issue, more and more cloud service providers introduce new pricing policies considering Dynamic Voltage and Frequency Scaling (DVFS), where users are charged on the basis of allocated CPU frequencies together with various combinations of VM configurations and prices. However, the customizable CPU frequencies make resource provisioning and scheduling harder to achieve a cost-optimal solution. The things become even worse, since lowering CPU voltages of VMs will increase their chance of suffering soft errors, which results in a high rate of completion time failures of workflow applications. To address the above problem, this paper proposes a novel task scheduling method for the purpose of cost optimization based on the genetic algorithm. By introducing new genetic operators and frequency scaling scheme for DVFS-enabled cloud workflows, our approach can quickly figure out cost-optimal resource provisioning and task scheduling solutions by allocating tasks to appropriate VMs with specific operating frequencies under energy, reliability, makespan and memory constraints. Extensive experiments on various well-known scientific workflow benchmarks validate the effectiveness of the proposed method. Comparing with state-of-the-art methods, our approach can significantly reduce the overall cost and energy consumption without violating the given constraints.

The 6G network enables a subnetwork-wide evolution, resulting in a “network of subnetworks”. However, due to the dynamic mobility of wireless subnetworks, the data transmission of intra-subnetwork and inter-subnetwork will inevitably interfere with each other, which poses a great challenge to radio resource management. Moreover, most existing approaches require the instantaneous channel gain between subnetworks, which are usually difficult to be collected. To tackle these issues, in this paper we propose a novel effective intelligent radio resource management method using multi-agent deep reinforcement learning (MARL), which only needs the sum of received power, named received signal strength indicator (RSSI), on each channel instead of channel gains. However, to directly separate individual interference from RSSI is an almost impossible thing. To this end, we further propose a novel MARL architecture, named GA-Net, which integrates a hard attention layer to model the importance distribution of inter-subnetwork relationships based on RSSI and excludes the impact of unrelated subnetworks, and employs a graph attention network with a multi-head attention layer to exact the features and calculate their weights that will impact individual throughput. Experimental results prove that our proposed framework significantly outperforms both traditional and MARL-based methods in various aspects.

Machine learning-based DDoS attack detection methods are mostly implemented at the packet level with expensive computational time costs, and the space cost of those sketch-based detection methods is uncertain. This paper proposes a two-stage DDoS attack detection algorithm combining time series-based multi-dimensional sketch and machine learning technologies. Besides packet numbers, total lengths, and protocols, we construct the time series-based multi-dimensional sketch with limited space cost by storing elephant flow information with the Boyer-Moore voting algorithm and hash index. For the first stage of detection, we adopt CNN to generate sketch-level DDoS attack detection results from the time series-based multi-dimensional sketch. For the sketch with potential DDoS attacks, we use RNN with flow information extracted from the sketch to implement flow-level DDoS attack detection in the second stage. Experimental results show that not only is the detection accuracy of our proposed method much close to that of packet-level DDoS attack detection methods based on machine learning, but also the computational time cost of our method is much smaller with regard to the number of machine learning operations.

As a newly proposed DNN architecture, MLP-Mixer is attracting increasing attention due to its competitive results compared to CNNs and attention-base networks in various tasks. Although MLP-Mixer only contains MLP layers, it still suffers from high communication costs in edge computing scenarios, resulting in long inference time. To improve the inference performance of an MLP-Mixer model on correlated resource-constrained heterogeneous edge devices, this paper proposes a novel partition and fusion method specific for MLP-Mixer layers, which can significantly reduce the communication costs. Experimental results show that, when the number of devices increases from 2 to 6, our partition and fusion method can archive 1.01-1.27x and 1.54-3.12x speedup in scenarios with heterogeneous and homogeneous devices, respectively.

Although Reinforcement Learning (RL) has achieved significant success in the Traffic Signal Control (TSC), most of them focus on the design of RL elements while the impact of the phase duration is neglected. Due to the lack of exploring dynamic phase duration, the overall performance and convergence rate of RL-based TSC approaches cannot be guaranteed, which may result in poor adaptability of RL methods to different traffic conditions. To address these issues, in this paper, we formulate a novel phase-duration-aware TSC (PDA-TSC) problem and propose an effective RL-based TSC approach, named MonitorLight. Our approach adopts a new traffic indicator, mixed pressure, which enables RL agents to simultaneously analyze the impacts of stationary and moving vehicles on intersections. Based on the observed mixed pressure of intersections, RL agents can autonomously determine whether or not to change the current signals in real-time. In addition, MonitorLight can adjust the control method for scenarios with different real-time requirements and achieve excellent results in different situations. Extensive experiments on both real-world and synthetic datasets demonstrate that MonitorLight outperforms the current state-of-the-art IPDALight by up to 2.84% and 5.71% in average vehicle travel time, respectively. Moreover, our method significantly speeds up the convergence, leading IPDALight by 36.87% and 34.58% in the start to converge episode and jumpstart performance, respectively.

Most of existing Neural Network (NN)-based barrier certificate synthesis methods cannot deal with high-dimensional continuous systems, since a large quantity of sampled data may easily result in inaccurate initial models coupled with slow convergence rate. To accelerate the synthesis of NN-based barrier certificates, this paper presents an effective two-stage approach named CL-BC, which fully exploits the parallel processing capability of underlying hardware to enable quick search for a barrier certificate. Unlike existing NN-based methods that adopt a random initial model for barrier certificate synthesis, in the first stage CL-BC pre-trains an initial model based on a small subset of sampling data. In this way, an approximate barrier certificate in an NN form can be quickly achieved with little overhead. Based on our proposed collaborative learning scheme, in the second stage CL-BC conducts the parallel learning on partitioned domains, where the learned knowledge from different partitions can be aggregated to accelerate the convergence of a global NN model for barrier certificate synthesis. In this way, the overall synthesis time of an NN-based barrier certificate can be drastically reduced. Experimental results show that our approach can not only drastically reduce barrier synthesis time, but also can synthesize barrier certificates for complex systems that cannot be handled by state-of-the-art.

Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs). Although the state-of-the-art method Neural Attention Distillation (NAD) can effectively erase backdoor triggers from DNNs, it still suffers from non-negligible Attack Success Rate (ASR) together with lowered classification ACCuracy (ACC), since NAD focuses on backdoor defense using attention features (i.e., attention maps) of the same order. In this paper, we introduce a novel backdoor defense framework named Attention Relation Graph Distillation (ARGD), which fully explores the correlation among attention features with different orders using our proposed Attention Relation Graphs (ARGs). Based on the alignment of ARGs between teacher and student models during knowledge distillation, ARGD can more effectively eradicate backdoors than NAD. Comprehensive experimental results show that, against six latest backdoor attacks, ARGD outperforms NAD by up to 94.85% reduction in ASR, while ACC can be improved by up to 3.23%.

Recent advancements in Convolution Neural Networks (CNNs) have achieved amazing success in numerous applications. The record-breaking performance of CNNs is usually at the prohibitive training costs, thus all training data are usually processed at the powerful centralized server side, which rises privacy concerns. Federated learning (FL) is a distributed machine learning method over mobile devices to train a global model while keeping decentralized data on devices to preserve the data privacy. However, there are two major limitations to deploy FL on mobile clients. Firstly, on the client side, the limited communication and computation resources on mobile devices cannot well support the full training iterations. Secondly, on the server side, conventional FL only aggregate a common output for all the clients without personalizing the model to each client, which is an important missing feature when clients have heterogeneous data distributions. In this work, we aim to enable low-cost personalized FL by focusing on the weight gradients which are the most important exchanging parameters in FL and meanwhile, dominating the computation and communication cost. We first observe that the client's calculated weight gradients have high sparsity, and the sparse pattern in weight gradients could be predicted via very simple bit-wise operations on a sequence of bits (named bit-stream) instead of conducting expensive high-precision calculations to determine them. Furthermore, a unique pattern is exhibited in each client's uploaded weight gradients according to the distribution of its local training data. Guided by this pattern, each client can get a personalized aggregated model to fit its own data. Hence, we leverage bit-streams to predict weight gradients sparsity for low-cost training on each device, and meanwhile, bit-streams are used to represent the unique sparse pattern of the weight gradient for each client which will guide the model personalization. From our experiments, our proposed framework can improve the computation efficiency by 3.5× on average (up to 4.2×) and reduce the communication cost by 23% on average (up to 41%) while still achieving the state-of-the-art personalized accuracy.

Due to the outstanding competence in capturing long-range relationships, self-attention mechanism has achieved remarkable progress in point cloud tasks. Nevertheless, point cloud object often has complex non-Euclidean spatial structures, with the behavior changing dynamically and unpredictably. Most current self-attention modules highly rely on the dot product multiplication in Euclidean space, which cannot capture internal non-Euclidean structures of point cloud objects, especially the long-range relationships along the curve of the implicit manifold surface represented by point cloud objects. To address this problem, in this paper, we introduce a novel metric on the Riemannian manifold to capture the long-range geometrical dependencies of point cloud objects to replace traditional self-attention modules, namely, the Geodesic Self-Attention (GSA) module. Our approach achieves state-of-the-art performance compared to point cloud Transformers on object classification, few-shot classification and part segmentation benchmarks.

Knowledge tracing is a crucial task in intelligent tutoring systems.Aiming at the shortcomings of traditional knowledge tracing technology such as low prediction accuracy, overfitting and low utilization of multi-features, this paper proposes a knowledge tracing model SRGCA-M using multi-feature embedding with stacked residual GRU network.Compared with the traditional methods that only use the historical record of answering exercises, our approach utilizes a variety of features in the learning process of students to deep characterize students' learning.We increase the layers number of GRU network to expand the capacity of sequence learning and use residual connections to solve the problems of network degradation and vanishing gradient.We use the auto-encoder to solve the problem that the cross-feature encoding will rapidly increase the dimension of the input data.Comprehensive experimental results demonstrate that compared with various advanced techniques, our approach can not only achieve better performance of tracking knowledge changes of students but also fully utilize multi-feature information of students in the learning process.

Federated learning (FL) has been recognized as a promising collaborative on-device machine learning method in the design of Internet of Things (IoT) systems. However, most existing FL methods fail to deal with IoT applications that contain a variety of IoT devices equipped with different types of neural network (NN) models. This is because traditional FL methods assume that local models on devices should have the same architecture as the global model on cloud. To address this problem, we propose a novel framework named PervasiveFL that enables efficient and effective FL among heterogeneous IoT devices. Without modifying original local models, PervasiveFL installs one lightweight NN model named modellet on each device. By using the deep mutual learning (DML) and our entropy-based decision gating (EDG) method, modellets and local models can selectively learn from each other through soft labels using locally captured data. Meanwhile, since modellets are of the same architecture, the learned knowledge by modellets can be shared among devices in a traditional FL manner. In this way, PervasiveFL can be pervasively applied to any heterogeneous IoT system. Comprehensive experimental results on four well-known datasets show that PervasiveFL can not only pervasively enable FL among heterogeneous devices within a large-scale IoT system, but also significantly enhance the inference accuracy of heterogeneous IoT devices with low communication overhead.

In-situ(InS) server systems are typically deployed in special environments to handleInSworkloads which are generated from environmentally sensitive areas or remote places lacking modern power supply infrastructure. This special operating environment ofInSservers urges such systems to be powered by renewable energy. In addition, theInSsystems are vulnerable to soft errors due to the harsh environments they deploy. This article tackles the problem of allocating harvested energy to renewable powered servers and assigning theInSworkloads to these servers for optimizing throughput of both the overall system and individual servers under energy and reliability constraints. We perform the energy allocation based on system state. In particular, for systems in low energy state, we propose a game theoretic approach that models the energy allocation as a cooperative game among multiple servers and derives a Nash bargaining solution. To meet the reliability constraint, we analyze the reliability optimality of assigning tasks to multiple servers and design a reliability-aware task assignment heuristic based on the analysis. Experimental results show that with a small time overhead, the proposed energy allocation approach achieves a high throughput from perspectives of both the overall system and individual servers, and the proposed task assignment approach ensures an increased system reliability.

The main goal of a cloud provider is to make profits by providing services to users. Existing profit optimization strategies employ homogeneous user models in which user personality is ignored, resulting in fewer profits and particularly notably lower user satisfaction that in turn, leads to fewer users and reduced profits. In this article, we propose efficient personality-aware request scheduling schemes to maximize the profit of the cloud provider under the constraint of user satisfaction. Specifically, we first model the service requests at the granularity of individual personality and propose a personalized user satisfaction prediction model based on questionnaires. Subsequently, we design a personality-guided integer linear programming (ILP)-based request scheduling algorithm to maximize the profit under the constraint of user satisfaction, which is followed by an approximate but lightweight value assessment and cross entropy (VACE)-based profit improvement scheme. The VACE-based scheme is especially tailored for applications with high scheduling resolution. Extensive simulation results show that our satisfaction prediction model can achieve the accuracy of up to 83 percent, and our profit optimization schemes can improve the profit by at least 3.96 percent as compared to the benchmarking methods while still obtaining a speedup of at least 1.68x.

As an efficient commercial computing paradigm, cloud computing provides various computing and storage resources to users in a pay-as-you-go manner. However, existing cloud pricing models and mechanisms are deterministic to some degree, thus, may not work well in a real-world environment where user perceived values with respect to cloud services are dynamically changing and highly personalized. In this article, we develop a reinforcement learning (RL)-based dynamic cloud pricing scheme to optimize both cloud provider’s profit and costs of heterogeneous users with distinct personalities. Specifically, we first propose a novel personality-guided user perceived value prediction scheme to proactively capture the dynamics of the users’ perceived values with respect to cloud services. The prediction scheme models the relationship among user personality, service price, quality of service (QoS), user satisfaction and perceived value in the cloud service market. Second, on the basis of the prediction model, a RL-based cloud pricing mechanism is developed to learn sequential service pricing decision-making for profit and costs optimization. Particularly, the profit and costs optimization problem is modeled as a discrete-time Markov decision process (MDP) that is solved by using Q-learning. Finally, extensive simulation experiments have been conducted to verify our user perceived value prediction scheme and RL-based cloud service pricing mechanism. Simulation results show that our perceived value prediction scheme can achieve up to 87.50 percent prediction accuracy, and our RL-based pricing mechanism can obtain up to 19.39 percent more profit than the state-of-the-art scheme.

Although Reinforcement Learning (RL) has been successfully applied in traffic control, it suffers from the problems of high average vehicle travel time and slow convergence to optimized solutions. This is because, due to the scalability restriction, most existing RL-based methods focus on the optimization of individual intersections while the impact of their cooperation is neglected. Without taking all the correlated intersections as a whole into account, it is difficult to achieve global optimization goals for complex traffic scenarios. To address this issue, this paper proposes a novel federated reinforcement learning approach named FedLight to enable optimal signal control policy generation for multi-intersection traffic scenarios. Inspired by federated learning, our approach supports knowledge sharing among RL agents, whose models are trained using decentralized traffic data at intersections. Based on such model-level collaborations, both the overall convergence rate and control quality can be significantly improved. Comprehensive experimental results demonstrate that compared with the state-of-the-art techniques, our approach can not only achieve better average vehicle travel time for various multi-intersection configurations, but also converge to optimal solutions much faster.

The unprecedented growth of mobile data traffic brings unique challenges for network bandwidth and server resources to meet the diverse QoE (Quality of Experience). Caching becomes a promising way to alleviate these issues by storing a subset of data at the network edge, for which caching policy becomes critical. To this end, various caching schemes have been put forward, however, these schemes are either not intelligent lacking the ability of self-learning and self-decision-making, or inefficient with low data hit rate. Based on these observations, in this paper, we propose a novel Intelligent Caching framework at the Edge, named ICE, via deep reinforcement learning to capture certain valued information of the requested data. Notably, in our approach, the popularity of the data to be cached will be explored and considered. A Markov decision model is further developed to determine whether the data should be cached. The evaluation shows that ICE greatly improves the hit rate in comparison with the state-of-the-art approaches, and reduces the energy consumption for data transmission. Furthermore, based on ICE, the users' QoE is greatly improved. In conclusion, both theoretical analysis and experimental results prove the effectiveness and high performance of ICE compared with conventional strategies.

The Clock Constraint Specification Language (CCSL) has become popular for modeling and analyzing timing behaviors of real-time embedded systems. However, it is difficult for requirement engineers to accurately figure out CCSL specifications from natural language-based requirement descriptions. This is mainly because: i) most requirement engineers lack expertise in formal modeling; and ii) few existing tools can be used to facilitate the generation of CCSL specifications. To address these issues, this paper presents a novel approach that combines the merits of both Reinforcement Learning (RL) and deductive techniques in logical reasoning for efficient co-synthesis of CCSL specifications. Specifically, our method leverages RL to enumerate all the feasible solutions to fill the holes of incomplete specifications and deductive techniques to judge the quality of each trial. Our proposed deductive mechanisms are useful for not only pruning enumeration space, but also guiding the enumeration process to reach an optimal solution quickly. Comprehensive experimental results on both well-known benchmarks and complex industrial examples demonstrate the performance and scalability of our method. Compared with the state-of-the-art, our approach can drastically reduce the synthesis time by several orders of magnitude while the accuracy of synthesis can be guaranteed.

Abstract In recent years, the advance in information technology has promoted a wide span of emerging cyber‐physical systems (CPS) applications such as autonomous automobile systems, healthcare monitoring, and process control systems. For these CPS applications, service latency management is extraordinarily important for the sake of providing high quality‐of‐experience to terminal users. Edge‐cloud computing, integrating both edge computing and cloud computing, is regarded as a promising computation paradigm to achieve low service latency for terminal users in CPS. However, existing latency‐aware edge‐cloud computing methods dedicated for CPS fail to jointly consider energy budgets and reliability requirements, which may greatly degrade the sustainability of CPS applications. In this article, we explore the problem of minimizing service latency of edge‐cloud computing coupled CPS under the constraints of energy budgets and reliability requirements. We propose a two‐stage approach composed of static and dynamic service latency optimization. At static stage, Monte‐Carlo simulation with integer‐linear‐programming technique is adopted to find the optimal computation offloading mapping and task backup number. At dynamic stage, a backup‐adaptive dynamic mechanism is developed to avoid redundant data transmissions and executions for achieving additional energy savings and service latency enhancement. Experimental results show that our solution is able to reduce system service latency by up to 18.3% compared with representative baseline solutions.

Automatic analysis of biomedical signals plays an important role in the auxiliary diagnosis of diseases. Traditional methods extract hand-crafted features by imitating doctors' experience, while recent methods focus on extracting deep features automatically by designing the architectures of deep neural networks (DNNs). Combining these two kinds of features can not only take advantage of doctors' experience but also mine the hidden information in the raw data. But directly combining these features by fully connected layers may cause complex optimization hyper-planes. To better integrate doctors' experience and deep features that doctors can hardly describe, we propose a feature fusion framework named hybrid plus framework (HPF) and apply this framework to seizure detection. HPF mainly consists of two parts: (1) the FET module, where hand-crafted features are extracted and transformed to sparse categorical features; (2) the enhanced DNN, which contains a carefully designed neural network structure with the input being original signals and sparse categorical features. Experiments on the dataset of CHB-MIT show that HPF outperforms the state-of-the-art methods. Further experiments indicate that HPF is very flexible as many of its modules can be replaced.

Modern software systems, either system or application software, are increasingly being developed on top of virtualized software platforms. They may simply intend to execute on virtual machines or they may be expected to port to physical machines eventually. In either case, the devices, virtual or silicon, in the target virtual or physical machines are expected to conform to the specifications based on which the software systems have been developed. Non-conformance of these devices to the specifications can cause catastrophic failures of the software systems. In this article, we propose a mutation-based framework for effective and efficient conformance checking between virtual/silicon device implementations and their specifications. Based on our defined mutation operators, device specifications can be automatically instrumented with weak mutant-killing constraints to model potential erroneous device behaviors. To kill all feasible mutants, our approach adopts a cooperative symbolic execution mechanism that can efficiently automate the test case generation and conformance checking for virtual/silicon devices. By symbolically executing the instrumented specifications with virtual/silicon device traces obtained from the cooperative execution, our method can accurately measure whether the designs have been sufficiently validated and report the inconsistencies between device specifications and implementations. Comprehensive experiments on two industrial network adapters and their virtual devices demonstrate the effectiveness of our proposed approach in conformance checking for both virtual and silicon devices.

As the density of integrated circuits continues to increase, the possibility that real-time systems suffer from soft and hard errors rises significantly, resulting in a degraded availability of system. In this article, we investigate the dynamic modeling of cross-layer soft error rate based on the Back Propagation (BP) neural network, and propose optimization strategies for system availability based on Cross Entropy (CE) and Q-learning algorithms. Specifically, the BP neural network is trained using cross-layer simulation data obtained from SPICE simulation while the optimization for system availability is achieved by judiciously selecting an optimal supply voltage for processors under timing constraints. Simulation results show that the CE-based method can improve system availability by up to 32 percent compared to state-of-the-art methods, and the Q-learning-based algorithm can further enhance system availability by up to 20 percent compared to the proposed CE-based method.

As a promising method for central model training on decentralized device data without compromising user privacy, federated learning (FL) is becoming more and more popular in Internet-of-Things (IoT) design. However, due to limited computing and memory resources of devices that restrict the capabilities of hosted deep learning models, existing FL approaches for artificial intelligence IoT (AIoT) applications suffer from inaccurate prediction results. To address this problem, this article presents a collaborativeBig.Littlebranch architecture to enable efficient FL for AIoT applications. Inspired by the architecture of BranchyNet which has multiple prediction branches, our approach deploys deep neural network (DNN) models across both cloud and AIoT devices. OurBig.Littlebranch model has two branches, where the big branch is deployed on cloud for strengthened prediction accuracy, and the little branches are used to fit for AIoT devices. When AIoT devices cannot make the prediction with high confidence using local little branches, they will resort to the big branch for further inference. To increase both prediction accuracy and early exit rate ofBig.Littlebranch model, we propose a two-stage training and coinference scheme, which considers the local characteristics of AIoT scenarios. Comprehensive experiment results obtained from a real AIoT environment demonstrate the efficiency and effectiveness of our approach in terms of prediction accuracy and average inference time.

Along with the proliferation of artificial intelligence and Internet of things (IoT) techniques, various kinds of adversarial attacks are increasingly emerging to fool deep neural networks (DNNs) used by industrial IoT (IIoT) applications. Due to biased training data or vulnerable underlying models, imperceptible modifications on inputs made by adversarial attacks may result in devastating consequences. Although existing methods are promising in defending such malicious attacks, most of them can only deal with limited existing attack types, which makes the deployment of large-scale IIoT devices a great challenge. To address this problem, in this article, we present an effective federated defense approach named FDA3that can aggregate defense knowledge against adversarial examples from different sources. Inspired by federated learning, our proposed cloud-based architecture enables the sharing of defense capabilities against different attacks among IIoT devices. Comprehensive experimental results show that the generated DNNs by our approach can not only resist more malicious attacks than existing attack-specific adversarial training methods, but also prevent IIoT applications from new attacks.

Convolutional Neural Networks (CNNs) are becoming popular in Internet-of-Things (IoT) based object tracking areas, e.g., autonomous driving, commercial surveillance, and intelligent traffic management. However, due to limited processing power of embedded devices and network bandwidth, how to simultaneously guarantee fast object tracking with high accuracy and low energy consumption is still a major challenge, which makes IoT-based vision applications unreliable and unsustainable. To address this problem, this article proposes a collaborative edge-cloud architecture that resorts to cloud for object tracking performance enhancement. By properly offloading computations to cloud and periodically checking tracking status of edge devices through convolutional Siamese networks, our novel edge-cloud architecture enables interactive collaborations between edge devices and cloud servers in order to quickly and accurately rectify tracking errors. Comprehensive experimental results on well-known video object tracking benchmarks show that our architecture can not only significantly improve the performance of object tracking, but also can save the energy consumption of edge devices.

The Clock Constraint Specification Language (CCSL) is a logical time based modeling language to formalize timing behaviors of real-time and embedded systems. However, it cannot capture timing behaviors that contain uncertainties, e.g., uncertainty in execution time and period. This limits the application of the language to real-world systems, as uncertainty often exists in practice due to both internal and external factors. To capture uncertainties in timing behaviors, in this paper we extend CCSL by introducing parameters into constraints. We then propose an approach to transform parametric CCSL constraints into SMT formulas for efficient verification. We apply our approach to an industrial case which is proposed as the FMTV (Formal Methods for Timing Verification) Challenge in 2015, which shows that timing behaviors with uncertainties can be effectively modeled and verified using the parametric CCSL.

Ordinary users can build their smart home automation system easily nowadays, but such user-customized systems could be error-prone. Using formal verification to prove the correctness of such systems is necessary. However, to conduct formal proof, formal specifications such as Linear Temporal Logic (LTL) formulas have to be provided, but ordinary users cannot author LTL formulas but only natural language.To address this problem, this paper presents a novel approach that can automatically generate formal LTL specifications from natural language requirements based on domain knowledge and our proposed ambiguity refining techniques. Experimental results show that our approach can achieve a high correctness rate of 95.4% in converting natural language sentences into LTL formulas from 481 requirements of real examples.

Streaming applications come from various application fields such as physics, and many can be represented as a series-parallel dependence graph. We aim at minimizing the energy consumption of such applications when executed on a hierarchical platform, by proposing novel mapping strategies. Dynamic voltage and frequency scaling (DVFS) is used to reduce the energy consumption, and we ensure a reliable execution by either executing a task at maximum speed, or by triplicating it. In this paper, we propose a structure rule to partition the series-parallel applications, and we prove that the optimization problem is NP-complete. We are able to derive a dynamic programming algorithm for the special case of linear chains, which provides an interesting heuristic and a building block for designing heuristics for the general case. The heuristics performance is compared to a baseline solution, where each task is executed at maximum speed. Simulations demonstrate that significant energy savings can be obtained.

Due to the merits of intuitive and visual modeling of design requirements, unified modeling language (UML) sequence diagrams are widely used as scenario-based specifications in the design of cyber-physical systems (CPSs). However, when more and more CPS products are deployed within an uncertain environment, existing sequence diagram analysis approaches cannot be used to accurately capture and quantify their timing behaviors at an early design stage. To address this problem, this article extends UML sequence diagrams to allow the modeling of stochastic system inputs, message processing time, and network delays, which strongly affect the system timing behaviors. We develop a statistical model checking-based framework that can automatically convert stochastic sequence diagrams into networks of priced timed automata to enable the quantitative analysis under various performance queries. The experimental results of two industrial designs in the railway field demonstrate the effectiveness of our approach.

Due to the existence of resource variations, it is very challenging for Cloud workflow resource allocation strategies to guarantee a reliable Quality of Service (QoS). Although dozens of resource allocation heuristics have been developed to improve the QoS of Cloud workflow, it is hard to predict their performance under variations because of the lack of accurate modeling and evaluation methods. So far, there is no comprehensive approach that can quantitatively reason the capability of resource allocation strategies or enable the tuning of parameters to optimize resource allocation solutions under variations. To address the above problems, this paper proposes a novel framework that can evaluate and optimize resource allocation strategies effectively and quantitatively. By using the statistical model checker UPPAAL-SMC and supervised learning approaches, our framework can: i) conduct complex QoS queries on resource allocation instances considering resource variations; ii) make quantitative and qualitative comparisons among resource allocation strategies; iii) enable the tuning of parameters to improve the overall QoS; and iv) support the quick optimization of overall workflow QoS under customer requirements and resource variations. The experimental results demonstrate that our automated framework can support both the Service Level Agreement (SLA) negotiation and workflow resource allocation optimization efficiently.

SQL injection attack (SQLIA) is among the most common security threats to web-based services that are deployed on cloud. By exploiting web software vulnerabilities, SQL injection attackers can run arbitrary malicious code on target databases to acquire or compromise sensitive data. Although web application firewalls (WAFs) are offered by most cloud service providers, tenants are reluctant to pay for them, since there are few approaches that can report accurate SQLIA statistics for their deployed services. Traditional WAFs focus on blocking suspicious SQL requests. Few of them can accurately decide whether an attack is really harmful and quickly answer how severe the attack is. To raise the tenants' awareness of the seriousness of SQLIAs, in this paper, we introduce a novel traffic-based SQLIA detection and vulnerability analysis framework named DIAVA, which can proactively send warnings to tenants promptly. By analyzing the bidirectional network traffic of SQL operations and applying our proposed multilevel regular expression model, DIAVA can accurately identify successful SQLIAs among all the suspects. Meanwhile, the severity of such SQLIAs and the vulnerabilities of the corresponding leaked data can be quickly evaluated by DIAVA based on its GPU-based dictionary attack analysis engine. Experimental results show that DIAVA not only outperforms state-of-the-art WAFs in detecting SQLAs from the perspectives of precision and recall, but also enables real-time vulnerability evaluation of leaked data caused by SQL injection.

To embrace the era of big data, there has been growing interest in designing distributed machine learning to exploit the collective computing power of the local computing nodes. Alternating Direction Method of Multipliers (ADMM) is one of the most popular methods. This method applies iterative local computations over local datasets at each agent and computation results exchange between the neighbors. During this iterative process, data privacy leakage arises when performing local computation over sensitive data. Although many differentially private ADMM algorithms have been proposed to deal with such privacy leakage, they still have to face many challenging issues such as low model accuracy over strict privacy constraints and requiring strong assumptions of convexity of the objective function. To address those issues, in this paper, we propose a differentially private robust ADMM algorithm (PR-ADMM) with Gaussian mechanism. We employ two kinds of noise variance decay schemes to carefully adjust the noise addition in the iterative process and utilize a threshold to eliminate the too noisy results from neighbors. We also prove that PR-ADMM satisfies dynamic zero-concentrated differential privacy (dynamic zCDP) and a total privacy loss is given by (∈, δ)-differential privacy. From a theoretical point of view, we analyze the convergence rate of PR-ADMM for general convex objectives, which is O(1/K) with K being the number of iterations. The performance of the proposed algorithm is evaluated on real-world datasets. The experimental results show that the proposed algorithm outperforms other differentially private ADMM based algorithms under the same total privacy loss.

The Clock Constraint Specification Language (CCSL) has been widely investigated in verifying causal and temporal timing behaviors of real-time embedded systems. However, due to limited expertise in formal modeling, it is difficult for requirement engineers to completely and accurately derive CCSL specifications from natural language-based design descriptions. To address this problem, we present a novel approach that facilitates automated synthesis of CCSL specifications under the guidance of sampled (expected) timing behaviors of target systems. By encoding sampled behaviors and incomplete CCSL constraints provided by requirement engineers using our proposed transformation templates, the CCSL specification synthesis problem can be naturally converted into a SKETCH synthesis problem, which enables the automated generation of CCSL specifications with high accuracy. Experiments on both well-known benchmarks and synthetic examples demonstrate the effectiveness and scalability of our approach.

As the density of integrated circuits continues to increase, the possibility that real-time systems suffer from transient and permanent failures rises significantly, resulting in a degraded availability of system functionality. In this paper, we investigate the dynamic modeling of transient failure rate based on Back Propagation (BP) neural network, and propose an optimization strategy for system availability based on Cross Entropy (CE). Specifically, the neural network is trained using cross-layer simulation data obtained from SPICE simulation while the CE-based optimization for system functionality availability is achieved by judiciously selecting an optimal supply voltage for processors under timing constraints. Simulation results show that the proposed method can achieve system availability improvement of up to 32% compared to benchmarking methods.

With the strong computation capability, NUMA-based multi-GPU system is a promising candidate to provide sustainable and scalable performance for Virtual Reality (VR) applications and deliver the excellent user experience. However, the entire multi-GPU system is viewed as a single GPU under the single programming model which greatly ignores the data locality among VR rendering tasks during the workload distribution, leading to tremendous remote memory accesses among GPU models (GPMs). The limited inter-GPM link bandwidth (e.g., 64GB/s for NVlink) becomes the major obstacle when executing VR applications in the multi-GPU system. By conducting comprehensive characterizations on different kinds of parallel rendering frameworks, we observe that distributing the rendering object along with its required data per GPM can reduce the inter-GPM memory accesses. However, this object-level rendering still faces two major challenges in NUMA-based multi-GPU system: (1) the large data locality between the left and right views of the same object and the data sharing among different objects and (2) the unbalanced workloads induced by the software-level distribution and composition mechanisms.

Benefiting from rich resources and virtualization technologies, hybrid cloud has emerged as a promising solution to processing large-scale scientific workflow applications for users in a pay-as-you-go manner. However, considering the complexity of resource configuration and deployment in hybrid clouds, existing workflow scheduling strategies designed for traditional distributed computing systems are limited and powerless. Therefore, for profit-driven infrastructure-as-a-service (IaaS) cloud providers, minimizing makespan and monetary cost of scheduling scientific workflows is an imperative concern. In this paper, we propose two efficient workflow scheduling approaches for hybrid clouds that both consider makespan and monetary cost. Specifically, we first propose a single-objective workflow scheduling optimization approach called DCOH (deadline-constrained cost optimization for hybrid clouds) for minimizing the monetary cost of scheduling workflows under deadline constraint. Based on DCOH, we further propose a multi-objective workflow scheduling optimization approach called MOH (multi-objective optimization for hybrid clouds) for optimizing makespan and monetary cost of scheduling workflows simultaneously. Extensive simulation experiments have been conducted to validate the effectiveness of DCOH and MOH. Simulation results show that our DCOH approach can reduce up to 100.0% monetary cost for users as compared to the competing algorithms under the same deadline constraint and our MOH approach can achieve better cost-makespan trade-off solutions as compared to the competing algorithms.

In recent years, the Internet of Things (IoT) has promoted many battery-powered emerging applications, such as smart home, environmental monitoring, and human healthcare monitoring, where energy management is of particular importance. Meanwhile, there is an accelerated tendency toward mobility of IoT devices, either being transported by humans or being mobile by itself. Existing energy management mechanisms for battery-powered IoT fail to consider the two significant characteristics of IoT: 1) the approximate real-time computation and 2) the mobility of IoT devices, resulting in unnecessary energy waste and network lifetime decay. In this paper, we explore mobility-aware network lifetime maximization for battery-powered IoT applications that perform approximate real-time computation under the quality-of-service (QoS) constraint. The proposed scheme is composed of offline and online stages. At offline stage, an optimal mobility-aware task schedule that maximizes network lifetime is derived by using mixed-integer linear programming technique. Redundant executions due to mobility-incurred overlapping of a single task on different IoT devices are avoided for energy savings. At online stage, a performance-guaranteed and time-efficient QoS-adaptive heuristic based on cross-entropy method is developed to adapt task execution to the fluctuating QoS requirements. Extensive simulations based on synthetic applications and real-life benchmarks have been implemented to validate the effectiveness of our proposed scheme. Experimental results demonstrate that the proposed technique can achieve up to 169.52% network lifetime improvement compared to benchmarking solutions.

With the advent of heterogeneous multiprocessor architectures, efficient scheduling for high performance has been of significant importance. However, joint considerations of reliability, temperature, and stochastic characteristics of precedence-constrained tasks for performance optimization make task scheduling particularly challenging. In this paper, we tackle this challenge by using an affinity (i.e., probability)-driven task allocation and scheduling approach that decouples schedule lengths and thermal profiles of processors. Specifically, we separately model the affinity of a task for processors with respect to schedule lengths and the affinity of a task for processors with regard to chip thermal profiles considering task reliability and stochastic characteristics of task execution time and intertask communication time. Subsequently, we combine the two types of affinities, and design a scheduling heuristic that assigns a task to the processor with the highest joint affinity. Extensive simulations based on randomly generated stochastic and real-world applications are performed to validate the effectiveness of the proposed approach. Experiment results show that the proposed scheme can reduce the system makespan by up to 30.1% without violating the temperature and reliability constraints compared to benchmarking methods.

EtherCAT has become one of the leading real-time Ethernet solutions for networked industrial systems, where a reliable communication infrastructure is needed due to highly error-prone environments. However, existing work on EtherCAT mainly focuses on clock synchronization and timeliness improvement. The reliability of EtherCAT-based networked systems has largely been ignored. In this paper, we present a proportional integral derivative (PID)-based feedback control scheme that aims at enhancing reliability of networked systems under timing and system resource constraints. Instead of retransmitting data upon error detection, we use forward error control technique based on inequality of arithmetic and geometric means to achieve the required system reliability at a low deadline miss rate of messages. We further optimize the forward error control technique and design a fast and fair error resilient mechanism by using a cooperative game. In addition to reliability enhancement, our PID-based error control scheme can also improve the stability of a system in terms of deadline miss rate in the presence of burst errors. Simulation results show that the proposed scheme can achieve reliability enhancement of up to 91% compared to benchmarking methods.

Computing systems utilize multicore processors with complex cache coherence protocols to meet the increasing need for performance and energy improvement. It is a major challenge to verify the correctness of a cache coherence protocol since the number of reachable states grows exponentially with the number of cores. In this paper, we propose an efficient test generation technique, which can be used to achieve full state and transition coverage in simulation-based verification for a wide variety of cache coherence protocols. Based on effective analysis of the state space structure, our method can generate more efficient test sequences (50% shorter) on-the-fly compared with tests generated by BFS. While our on-the-fly method can reduce the numbers of required tests by half, it can still be impractical to verify all possible transitions in the presence of large number of cores. We propose scalable on-the-fly test generation techniques using quotient state space. The proposed approach guarantees selection of important transitions by utilizing equivalence classes, and omits only similar transitions. Our experimental results demonstrate that our proposed approaches can efficiently tradeoff between transition coverage and validation effort.

Multiprocessor system-on-chip (MPSoC) has been widely used in many real-time embedded systems where both soft-error reliability (SER) and lifetime reliability (LTR) are key concerns. Many existing works have investigated them, but they focus either on handling one of the two reliability concerns or on improving one type of reliability under the constraint of the other. These techniques are thus not applicable to maximize SER and LTR simultaneously, which is highly desired in some real-world applications. In this paper, we study the joint optimization of SER and LTR for real-time MPSoCs. We propose a novel static task scheduling algorithm to simultaneously maximize SER and LTR for real-time homogeneous MPSoC systems under the constraints of deadline, energy budget, and task precedence. Specifically, we develop a new solution representation scheme and two evolutionary operators that are closely integrated with two popular multiobjective evolutionary optimization frameworks, namely NSGAII and SPEA2. Extensive experimental results on standard benchmarks and synthetic applications show the efficacy of our scheme. More specifically, our scheme can achieve significantly better solutions (i.e., LTR-SER tradeoff fronts) with remarkably higher hypervolume and can be dozens or even hundreds of times faster than the state-of-the-art algorithms. The results also demonstrate that our scheme can be applied to heterogeneous MPSoC systems and is effective in improving reliability for heterogeneous MPSoC systems.

Due to the increasing complexity of System-on-Chip (SoC) design, how to ensure that silicon implementations conform to their high-level specifications is becoming a major challenge. To address this problem, we propose a novel specification-driven conformance checking approach that can automatically identify inconsistencies between different levels of designs. By extending SystemRDL specifications, our approach enables the generation of high-level Formal Device Models (FDMs) that specify access behaviors of interface registers triggered by driver requests. Based on the symbolic execution of the generated FDMs with the same driver requests to virtual/silicon devices, our approach can efficiently check whether the designs of an SoC at different levels exhibit unexpected behaviors that are not modeled in the given specification. Experiments on two industrial network adapters demonstrate the effectiveness of our approach in troubleshooting bugs caused by inconsistencies in both virtual and post-silicon prototypes.

EtherCAT has become one of the leading real-time Ethernet solutions for networked industrial systems where a reliable communication infrastructure is needed due to highly error-prone environments. However, existing work on EtherCAT mainly focuses on clock synchronization and timeliness improvement. The reliability of EtherCAT-based networked systems has largely been ignored. In this paper, we present a PID-based feedback control scheme that aims at enhancing reliability of networked systems under timing and system resource constraints. Instead of automatic repeat request method (ARQ), a forward error control technique is introduced to achieve the required system reliability at a lower deadline miss rate of messages. The PID-based feedback control scheme can also improve the stability of a system in terms of deadline miss rate in the presence of bursty errors. Simulation results show that the proposed scheme can achieve reliability enhancement of up to 79% compared to benchmarking methods.

Both soft-error reliability (SER) due to transient faults and lifetime reliability (LTR) due to permanent faults are key concerns in real-time MPSoCs. Existing works have investigated related problems, however, most of them only focus on one of the two reliability concerns. A few efforts do consider both types of reliability together, but ignore the impacts of hardware- and application-level variations on reliability, thus are not applicable to state-of-the-art MPSoCs under variations. In this paper, we focus on increasing SER without sacrificing LTR since transient faults occur much more frequently than permanent faults. Specifically, we propose a novel task allocation and scheduling scheme to maximize SER while satisfying a LTR constraint for soft real-time MPSoCs. Considering that SER is the objective while LTR is a constraint in our problem, and LTR is highly related to core temperature profiles, we dedicate to investigating the effects of variations in core soft-error rate, task vulnerability to soft errors, and task execution time on SER. To the best of our knowledge, our work is the first attempt that jointly handles the two reliability issues as well as taking into account the effects of variations on reliability. Experimental results show that our scheme improves the SER by up to 66% as compared to a number of representative existing approaches while meeting the same LTR constraint.

Multi-Processor System-on-Chip (MPSoC) has emerged as a promising platform to meet the increasing performance demand of embedded applications. However, due to limited energy budget, it is hard to guarantee that applications on MPSoC can be accomplished on time with a required throughput. The situation becomes even worse for applications with high reliability requirements, since extra energy will be inevitably consumed by task re-executions or duplicated tasks. Based on Dynamic Voltage and Frequency Scaling (DVFS) and task duplication techniques, this paper presents a novel energy-efficient scheduling model, which aims at minimizing the overall energy consumption of MPSoC applications under both throughput and reliability constraints. The problem is shown to be NP-complete, and several polynomial-time heuristics are proposed to tackle this problem. Comprehensive simulations on both synthetic and real application graphs show that our proposed heuristics can meet all the given constraints, while reducing the energy consumption.

The main goal of a cloud service provider is to make profits by providing services to users. Existing pricing strategies adopt a single revenue function for different types of service requests, which ignores the heterogeneity of users and leads to low profits. In this paper, we propose a heterogeneity-aware request scheduling scheme that maximizes profits of service providers by exploiting the heterogeneity of users. Specifically, we first model charge functions of requests at the granularity of individual users to capture their heterogeneity. Then an integer linear programming (ILP)-based optimal scheduling algorithm is designed to maximize profits, which is followed by an approximate but lightweight genetic algorithm (GA)-based profit improvement scheme. The GA-based scheme is particularly tailored for applications of high scheduling resolution. Extensive simulation results show that our schemes improve profits by at least 22.46% compared to benchmarking methods while achieving at least 13.51 times of speedup.

Internet of Things devices, such as video-based detectors or road side units are being deployed in emerging applications like sustainable and intelligent transportation systems. Oftentimes, stringent operation and energy cost constraints are exerted on this type of applications, necessitating a hybrid supply of renewable and grid energy. The key issue of a cost-constrained hybrid of renewable and grid power is its uncertainty in energy availability. The characteristic of approximate computation that accepts an approximate result when energy is limited and executes more computations yielding better results if more energy is available, can be exploited to intelligently handle the uncertainty. In this paper, we first propose an energy-adaptive task allocation scheme that optimally assigns real-time approximate-computation tasks to individual processors and subsequently enables a matching of the cost-constrained hybrid supply of energy with the energy demand of the resultant task schedule. We then present a quality of service (QoS)-driven task scheduling scheme that determines the optional execution cycles of tasks on individual processors for optimization of system QoS. A dynamic task scheduling scheme is also designed to adapt at runtime the task execution to the varying amount of the available energy. Simulation results show that our schemes can reduce system energy consumption by up to 29% and improve system QoS by up to 108% as compared to benchmarking algorithms.

With the rapid deployment of cloud computing infrastructures, understanding the economics of cloud computing has become a pressing issue for cloud service providers. However, existing pricing models rarely consider the dynamic interactions between user requests and the cloud service provider. Thus, the law of supply and demand in marketing is not fully explored in these pricing models. In this paper, we propose a dynamic pricing model based on the concept of user perceived value that accurately captures the real supply and demand relationship in the cloud service market. Subsequently, a profit maximization scheme is designed based on the dynamic pricing model that optimizes profit of the cloud service provider without violating service-level agreement. Finally, a dynamic closed loop control scheme is developed to adjust the cloud service price and multiserver configurations according to the dynamics of the cloud computing environment such as fluctuating electricity and rental fees. Extensive simulations using the data extracted from real-world applications validate the effectiveness of the proposed user perceived value-based pricing model and the dynamic profit maximization scheme. Our algorithm can achieve up to 31.32 percent profit improvement compared to a state-of-the-art approach.

Aiming at high performance, more and more Cyber-Physical Systems (CPSs) adopt Multiprocessor System-on-Chips (MPSoCs) as computation units. However, due to increasing integration of transistors on a die, the power densities together with performance variations of MPSoC chips have been increasing dramatically. Consequently, the MPSoC-based CPSs might become unsustainable and unreliable. Although various Task Allocation and Scheduling (TAS) heuristics have been proposed to minimize the hotspot time (i.e., duration of thermal emergency) and energy consumption of MPSoC designs, few of them can guarantee the highest performance yield under process variations without violating energy, thermal and timing constraints. To address these challenges, this paper proposes a novel energy- and thermal-aware TAS evaluation and optimization framework. Based on statistical model checking techniques, our approach enables accurate modeling and reasoning of the performance yield of real-time MPSoC designs under joint energy and thermal constraints. To enable system-level design space exploration, we propose a regression analysis-based method that can drastically reduce the overall exploration efforts. Experimental results show that our fully-automated approach can not only allow accurate sustainability-oriented reasoning of TAS solutions under specified thermal and energy constraints, but also enable the quick search of optimal TAS solutions on different MPSoC architectures with the highest performance yield.

This paper proposes a novel input system via fingers touching, called FingerVoice. Instead of traditional letter based input system, it is based on syllables. Fingers on the left hand stand for consonants while fingers on the right hand for vowels. Fingers from both hands touch each other to form a syllable. We use a pair of gloves with conductive finger caps to detect the touch. As an example, the implementation of Chinese is presented in details. By connecting it to a smart phone via Bluetooth, a utility speaking system is implemented to help the speech-impaired to "speak" via smart phone. Our experimental result shows that this syllable based input device is faster than letter based input devices.

For modelling hybrid systems, we have extended Event B based on its framework with the differential event. The differential event describes continuous behaviors of hybrid systems by differential equations and evolution constraint, whose proof obligations provide dynamical properties of a model. In order to ensure the safety and reliability of a model, proof obligations should be proved. It is difficult to prove proof obligation in state space, because there is no a complete method to solve differential equations in the field of mathematics. Thus we proposed an approach to proving proof obligation based on differential invariants. It is to avoid uncontrollable computation on solving differential equation. The main result is that we prove some theorems for proving proof obligations involving differential events within the framework of refinement calculus. Lastly, through the case of the Train Control System, we further show that the approach is well suited.

Data flow testing (DFT) has been shown to be an effective testing strategy. DFT features a high fault detection rate while avoiding the intense scalability problems to achieve full path coverage. In this paper we propose to apply data flow testing for SystemC virtual prototypes (VPs). Our contribution is twofold: First, we develop a set of SystemC specific coverage criteria for data flow testing. This requires to consider the SystemC semantics of using non-preemptive thread scheduling with shared memory communication and event-based synchronization. Second, we explain how to automatically compute the data flow coverage result for a given VP using a combination of static and dynamic analysis techniques. The coverage result provides clear suggestions for the testing engineer to add new testcases in order to improve the coverage result. Our experimental results on real-world VPs demonstrate the applicability and efficacy of our analysis approach and the SystemC specific coverage criteria to improve the testsuite.

The key issue of renewable generations such as solar and wind in energy harvesting system is the uncertainty of energy availability. The characteristic of imprecise computation that accepts an approximate result when energy is limited and executes more computations yielding better results if more energy is available, can be exploited to intelligently handle the uncertainty. In this paper, we first propose a task allocation scheme that adaptively assigns real-time imprecise computation tasks to individual processors considering uncertainties in renewable energy sources. The proposed task allocation scheme enhances energy efficiency by minimizing system energy consumption followed by adapting the execution of imprecise computation tasks to the energy availability. We then present a QoS-aware task scheduling scheme that determines the optional execution cycles of tasks allocated to processors. The proposed task scheduling scheme maximizes system QoS under the energy budget constraint.

With the rapid deployment of cloud computing infrastructures, understanding the economics of cloud computing has becoming a pressing issue for cloud service providers. However, existing pricing models rarely consider the dynamic interaction between user requests and the cloud service provider, thus can not accurately reflect the law of supply and demand in marketing. In this paper, we propose a pricing model based on the concept of user perceived value in the domain of economics that accurately capture the real supply and demand situation in the cloud service market. We then design a profit maximization scheme based on the presented dynamic pricing model that optimizes profit of the cloud service provider without violating user service-level agreement. Extensive experiments using data extracted from real-world applications validate the effectiveness of the proposed user perceived value-based pricing model. The proposed profit maximization scheme achieves 24.44% more profit as compared to the state of the art benchmarking methods.

The hybrid architecture analysis and design language (AADL) has been proposed to model the interactions between embedded control systems and continuous physical environment. However, the worst-case performance analysis of hybrid AADL designs often leads to overly pessimistic estimations, and is not suitable for accurate reasoning about overall system performance, in particular when the system closely interacts with an uncertain external environment. To address this challenge, this paper proposes a statistical model checking-based framework that can perform quantitative evaluation of uncertainty-aware hybrid AADL designs against various performance queries. Our approach extends hybrid AADL to support the modeling of environment uncertainties. Furthermore, we propose a set of transformation rules that can automatically translate AADL designs together with designers' requirements into networks of priced timed automata and performance queries, respectively. Comprehensive experimental results on the movement authority scenario of Chinese train control system level 3 demonstrate the effectiveness of our approach.

Mobile devices are quickly becoming the most widely used processors in consumer devices. Since their major power supply is battery, energy-efficient computing is highly desired. In this article, we focus on energy-efficient cache design in emerging mobile platforms. We observe that more than 40% of L2 cache accesses are OS kernel accesses in interactive smartphone applications. Such frequent kernel accesses cause serious interferences between the user and kernel blocks in the L2 cache, leading to unnecessary block replacements and high L2 cache miss rate. We first propose to statically partition the L2 cache into two separate segments, which can be accessed only by the user code and kernel code, respectively. Meanwhile, the overall size of the two segments is shrunk, which reduces the energy consumption while still maintaining the similar cache miss rate. We then find completely different access behaviors between the two separated kernel and user segments and explore the multi-retention STT-RAM-based user and kernel segments to obtain higher energy savings in this static partition-based cache design. Finally, we propose to dynamically partition the L2 cache into the user and kernel segments to minimize overall cache size. We also integrate the short-retention STT-RAM into this dynamic partition-based cache design for maximal energy savings. The experimental results show that our static technique reduces cache energy consumption by 75% with 2% performance loss, and our dynamic technique further shows strong capability to reduce cache energy consumption by 85% with only 3% performance loss.

Branch-and-bound (B&B) approaches are widely investigated in resource constrained scheduling (RCS). However, due to the lack of approaches that can generate a tight schedule at the beginning of the search, B&B approaches usually start with a large initial search space, which makes the following search of an optimal schedule time-consuming. To address this problem, this paper proposes a parallel two-phase B&B approach that can drastically reduce the overall RCS time. This paper makes three major contributions: i) it proposes three partial-search heuristics that can quickly find a tight schedule to compact the initial search space; ii) it presents a two-phase search framework that supports the efficient parallel search of an optimal schedule; iii) it investigates various bound sharing and speculation techniques among collaborative tasks to further improve the parallel search performance at different search phases. The experimental results based on well-established benchmarks demonstrate the efficacy of our proposed approach.

Structure coverage driven test generation is the key approach for automatic testing at source code level. However, the defect detection ability of the generated test cases should be carefully evaluated since the correlation between coverage and test effectiveness is in doubt. In this paper, we propose a test generation approach based on mutation testing with the intent to derive test cases towards finding defects rather than just covering certain syntactic structures. Moreover, instead of generating test cases from the code under test directly, we base our approach on UML activity diagrams to make it possible to decide verdicts of test inputs. Mutation operators for activity diagrams are defined and the test generation algorithms are based on solving mutated path constraints. Experimental results have shown that by applying the proposed mutated testing approach, test cases with higher defect detection ability can be generated.

In-situ server systems are deployed in very special operating environment to handle in-situ workloads that are normally generated from environmentally sensitive areas or remote places that lack established utility infrastructure. This very special operating environment of in-situ servers urges such systems to be 100 percent powered by renewable energy. However, existing energy management schemes assume a hybrid supply of grid and renewable energy, hence are not well suited for 100 percent renewable powered in-situ server systems. In this paper, we tackle the problem of allocating harvested energy to 100 percent renewable powered server systems for optimizing both the overall system throughput and throughput of individual servers. From a game theoretic perspective, we model the energy allocation problem as a cooperative game among multiple servers and derive a Nash bargaining solution. Based on the Nash bargaining solution, we then propose a heuristic algorithm that determines the energy allocation strategies according to system energy states. Experimental results show that our proposed game theoretic approach achieves a high throughput from perspectives of both the overall system and individual servers.

Since Internet of Things (IoT) applications are deployed within open physical environments, their executions suffer from a wide spectrum of uncertain factors (e.g., network delay, sensor inputs). Although ThingML is a promising IoT modeling and specification language which enables the fast development of resource-constrained IoT applications, it lacks the capability to model such uncertainties and quantify their effects. Consequently, within uncertain environments the quality and performance of IoT applications generated from ThingML designs cannot be guaranteed. To explore the overall runtime performance variations caused by environmental uncertainties, this paper proposes a quantitative uncertainty evaluation framework for ThingML-based IoT designs. By adopting network of priced timed automata as the model of computation and statistical model checking as the evaluation engine, our approach can model uncertainties caused by external environments as well as support various kinds of performance queries on the extended ThingML designs. Experimental results of two comprehensive case studies demonstrate the efficacy of our approach.

For many old buildings in the world, due to the legacy devices problem, it is hard to supply appropriate energy for them.In order to reduce the energy consumption of buildings under the premise of satisfying user requirements, we use software control systems whose core part is the scheduling strategy, to reconstruct them.It is time consuming to choose a good scheduling strategy due to many uncertain factors, among which user actions are of the most influence.In this paper, we propose an Support Vector Machine (SVM) based approach to explore the relation between user action and the best scheduling strategy of a control system.The main contributions include:(1) obtaining the sample set by collecting data at the model level using Statistical Model Checking (SMC) based method; (2) using SVM algorithm to learn the relation model between user actions and the best scheduling strategies; and (3) applying the relation model to predict a best scheduling strategy.Finally a real case study is conducted showing the efficiency of our approach.

Branch-and-bound approaches are promising in pruning fruitless search space during the resource constrained scheduling. However, such approaches only compare the estimated upper and lower bounds of an incomplete schedule to the length of the best feasible schedule at that iteration, which does not fully exploit the potential of the pruning during the search. Aiming to improve the performance of resource constrained scheduling, this paper proposes a parallel structure-aware pruning approach that can traverse the search space significantly faster than state-of-the-art branch-and-bound techniques. This paper makes three major contributions: i) it proposes an efficient pruning technique using the structural scheduling information of the obtained best feasible schedules; ii) it investigates how to perform parallel search to enable efficient multi-directional search and generation of effective fences by tuning the operation enumeration order; and iii) it presents a framework that supports the sharing of minimum upper-bound and fence information among different search tasks to enable efficient parallel structure-aware pruning. The experimental results demonstrate that our parallel pruning approach can drastically reduce the overall resource constrained scheduling time under a wide variety of resource constraints.

With the continuous scaling of CMOS devices, the increase in power density and system integration level have not only resulted in huge energy consumption but also led to elevated chip temperature. Thus, energy efficient task scheduling with thermal consideration has become a pressing research issue in computing systems, especially for real-time embedded systems with limited cooling techniques. In this paper, we design a two-stage energy-efficient temperature-aware task scheduling scheme for heterogeneous real-time multiprocessor system-on-chip (MPSoC) systems. In the first stage, we analyze the energy optimality of assigning real-time tasks to multiple processors of an MPSoC system, and design a task assignment heuristic that minimizes the system dynamic energy consumption under the constraint of task deadlines. In the second stage, the optimality of minimizing the peak temperature of a processor is investigated, and a slack distribution heuristic is proposed to improve the temperature profile of each processor under the thermal constraint, thus the temperature-dependent system leakage energy consumption is reduced. Through the extensive efforts made in two stages, the system overall energy consumption is minimized. Experimental results have demonstrated the effectiveness of our scheme.

The increasing adoption of graphics processing units (GPUs) for high-performance computing raises the reliability challenge, which is generally ignored in traditional GPUs. GPUs usually support thousands of parallel threads and require a sizable register file. Such large register file is highly susceptible to soft errors and power-hungry. Although ECC has been adopted to register file in modern GPUs, it causes considerable power overhead, which further increases the power stress. Thus, an energy-efficient soft-error protection mechanism is more desirable. Besides its extremely low leakage power consumption, resistive memory (e.g., spin-transfer torque RAM) is also immune to the radiation induced soft errors due to its magnetic field based storage. In this article, we propose to LEverage reSistive memory to enhance the Soft-error robustness and reduce the power consumption (LESS) of registers in the General-Purpose computing on GPUs (GPGPUs). Since resistive memory experiences longer write latency compared to SRAM, we explore the unique characteristics of GPGPU applications to obtain the win-win gains: achieving the near-full soft-error protection for the register file, and meanwhile substantially reducing the energy consumption with negligible performance degradation. Our experimental results show that LESS is able to mitigate the registers soft-error vulnerability by 86% and achieve 61% energy savings with negligible (e.g., 1%) performance degradation.

As technology keeps scaling down, hardware variability, such as process variations (PV) and negative bias temperature instability (NBTI), emerges as a growing challenge in the modern GPGPUs (general-purpose computing on graphics processing units). PV induces significant delay variations statically, while NBTI dynamically slows down the GPGPUs. Each computing core (i.e., streaming multiprocessor) in GPGPUs supports thousands of simultaneously active threads, and requires a large register file. Such a sizable register file is very sensitive to the hardware variability, and becomes one of the major units in determining the core frequency. In this study, we propose a set of techniques that mitigate both the PV and NBTI impacts on GPGPUs register file. In order to mitigate the susceptibility to PV, we first develop a novel mechanism that classifies registers into fast and slow categories in the highly-banked register architecture to maximize the frequency improvement. We then leverage the unique features in GPGPU applications to effectively tolerate the extra access delay to the slow registers. Moreover, we propose to dynamically balance the utilization across registers to further tolerate the NBTI degradation. Our experimental results show that our proposed techniques optimize GPGPUs performance by 22 percent on average under both PV and NBTI effects.

Energy consumption evaluation is one of the most important steps in Cyber-Physical Energy System (CPES) development. However, due to the lack of accurate and effective modeling and evaluation approaches considering the uncertainty of environment, it is hard to conduct the quantitative analysis for the energy consumption of CPESs. To address the above issue, this paper proposes an environment-aware energy consumption evaluation framework based on the Statistical Model Checking (SMC). In our framework, the environment uncertainty of CPESs is modeled using the Stochastic Hybrid Automata (SHA). In order to describe various environment modeling patterns, we create a collection of parameterized SHA models and save them to a domain specific environment ontology. Based on the domain environment ontology and user designs in the form of UML sequence diagrams and activity diagrams, our framework can automatically guide the construction of CPES models using networks of SHA and conduct the corresponding energy consumption evaluation. A case study based on an energy-aware building design demonstrates that our approach can not only support the accurate environment modeling with various uncertain factors, but also can be used to reason the relations between the energy consumption and environment uncertainties of CPES designs.

Runtime verification is a dynamic verification technique widely used in practice. In this paper we revisit the runtime verification technique with formula progression, which verifies the execution trace step by step by progressing the desired property written in temporal logic. The previous work did not discuss explicitly the bound for the sizes of expanded formulas, while the successive invoking of formula progression is likely to cause divergence. In this paper, we present the convergent formula progression by introducing a novel fix-point reduction technique, and prove it guarantees the sizes of expanded formulas be always convergent. To the best of our knowledge, this is the first work discussing the convergence of formula progression. Furthermore, we implement the new runtime verification framework, and experiments show the efficiency of our proposed strategy.

Cyber-Physical Systems (CPSs) integrate computing, communication and control processes. Close interactions between the cyber and physical worlds occur in time and space frequently. Therefore, both temporal and spatial information should be taken into consideration when specifying properties of CPS systems for verification. However, how to formulate properties specifying spatial together with temporal features is still an unsolved problem in the CPS. In this paper, we propose an approach to analyze the spatio-temproal properties of CPS. A spatio-temporal logic is developed, including the syntax and semantics of the logic. With that logic, properties of both states, transitions and global systems could be specified, paving the way for further verification. To show the efficiency of the approach, a Train Control System is introduced as a case study. Meanwhile, more details about how to specifying properties of CPS systems with our method are elaborated.

Precisely describing complicate interaction process is still an open problem in MARTE(Modeling and Analysis of Realtime Embedded System). In this paper, we propose an approach to modeling interaction behaviors to enhance MARTE modeling ability. MARTE is published by OMG(Object Management Group) in Aug, 2010 as a standard modeling language for modeling real time and embedded system. Our approach is based on timed CSP(Communicating Sequential Processes). To describe the multiform time structure in MARTE, we make an extension to timed CSP. The syntax and semantics of the communicating process specification are given and also the laws, the trace model and the failures model are defined. One of the main advantages of our method is to help people to modeling the complicate interaction process with process algebra, thus to simplify the modeling and verification of the interaction and concurrent behaviors in real-time and embedded systems between different processes. The approach is applied to model and analyze a Train Over Speed Protection System for Shanghai Bell Company.

SystemC transaction-level modeling (TLM) is widely used to enable early exploration for both hardware and software designs. It can reduce the overall design and validation effort of complex system-on-chip (SOC) architectures. However, due to lack of automated techniques coupled with limited reuse of validation efforts between abstraction levels, SOC validation is becoming a major bottleneck. This article presents a novel top-down methodology for automatically generating register transfer-level (RTL) tests from SystemC TLM specifications. It makes two important contributions: i) it proposes a method that can automatically generate TLM tests using various coverage metrics, and (ii) it develops a test refinement specification for automatically converting TLM tests to RTL tests in order to reduce overall validation effort. We have developed a tool which incorporates these activities to enable automated RTL test generation from SystemC TLM specifications. Case studies using a router example and a 64-bit Alpha AXP pipelined processor demonstrate that our approach can achieve intended functional coverage of the RTL designs, as well as capture various functional errors and inconsistencies between specifications and implementations.

SAT-based BMC is promising for directed test generation since it can locate the reason of an error within a small bound. However, due to the state space explosion problem, BMC cannot handle complex designs and properties. Although various optimization methods are proposed to address a single complex property, the test generation process cannot be fully automated. This paper presents an efficient automated approach that can scale down the falsification complexity using property decomposition and learning techniques. Our experimental results using both software and hardware benchmarks demonstrate that our approach can drastically reduce the overall test generation effort.

Property falsification in model checking is widely used for automated generation of directed tests. Due to state space explosion problem, traditional model checking techniques cannot handle large scale designs. SAT-based bounded model checking is promising to address the prohibitively large time and resource requirements during the property falsification. This article presents several efficient learning techniques that can improve the overall test generation time for a single property as well as a cluster of similar properties. The goal is to exploit both variable assignments and common conflict clauses of the prechecked partial or similar SAT instances for property falsification. Our method makes three novel contributions: 1) investigates the decision ordering-based learnings for a single SAT instance; 2) applies the decision ordering learnings between similar SAT instances; and 3) exploits the relation between the decision ordering-based learning and conflict clauses-based learning. Our experimental results using both software and hardware benchmarks demonstrate that our approach can drastically reduce the overall test generation time.

Model checking techniques are promising for automated generation of directed tests. However, due to the prohibitively large time and resource requirements, conventional model checking techniques do not scale well when checking complex designs. In SAT-based BMC, many variable ordering heuristics have been investigated to improve counterexample (test) generation involving only one property. This paper presents efficient decision ordering techniques that can improve the overall test generation time of a cluster of similar properties. Our method exploits the assignments of previously generated tests and incorporates it in the decision ordering heuristic for current test generation. Our experimental results using both software and hardware benchmarks demonstrate that our approach can drastically reduce the overall test generation time.

Functional verification is one of the major bottlenecks in system-on-chip design due to the combined effects of increasing complexity and lack of automated techniques for generating efficient tests. Several promising ideas using bounded model checking are proposed over the years to efficiently generate counterexamples (tests). The existing researchers have used incremental satisfiability to improve the counterexample generation, involving only one property by sharing knowledge across instances of the same property with incremental bounds. In this paper, we present a framework that can efficiently reduce the overall test generation time by exploiting the similarity among different properties. This paper makes two primary contributions: (1) it proposes novel methods to cluster similar properties; and (2) it develops efficient learning techniques that can significantly reduce the overall test generation time for the properties in a cluster by sharing knowledge across similar test generation instances. Our experimental results using both software and hardware benchmarks demonstrate that our approach can drastically reduce (on average three to five times) the overall test generation time compared to existing methods.

Test case generation based on design specifications is an important part of testing processes. In this paper, Unified Modeling Language activity diagrams are used as design specifications. By setting up several test adequacy criteria with respect to activity diagrams, an automatic approach is presented to generate test cases for Java programs. Instead of directly deriving test cases from activity diagrams, this approach selects test cases from a set of randomly generated ones according to a given test adequacy criterion. In the approach, we first instrument a Java program under testing according to its activity diagram model, and randomly generate abundant test cases for the program. Then, by running the instrumented program we obtain the corresponding program execution traces. Finally, by matching these traces with the behavior of the activity diagram, a reduced set of test cases are selected according to the given test adequacy criterion. This approach can also be used to check the consistency between the program execution traces and the behavior of activity diagrams.

Due to the increasing complexity of today's embedded systems, the analysis and validation of such systems is becoming a major challenge. UML is gradually adopted in the embedded system design as a system level specification. One of the major bottlenecks in the validation of UML activity diagrams is the lack of automated techniques for directed test generation. This paper proposes an automated test generation approach for the UML activity diagrams. The contribution of this paper is the use of specification coverage to generate properties as well as design models to enable directed test generation using model checking. Our experimental results demonstrate that our approach can drastically reduce the validation effort in both specification and implementation levels.