Abstract Deep neural network has achieved promising results for automatic glaucoma detection on fundus images. Nevertheless, the intrinsic discrepancy across glaucoma datasets is challenging for the data-driven neural network approaches. This discrepancy leads to the domain gap that affects model performance and declines model generalization capability. Existing domain adaptation-based transfer learning methods mostly fine-tune pretrained models on target domains to reduce the domain gap. However, this feature learning-based adaptation method is implicit, and it is not an optimal solution for transfer learning on the diverse glaucoma datasets. In this paper, we propose a mixup domain adaptation (mixDA) method that bridges domain adaptation with domain mixup to improve model performance across divergent glaucoma datasets. Specifically, the domain adaptation reduces the domain gap of glaucoma datasets in transfer learning with an explicit adaptation manner. Meanwhile, the domain mixup further minimizes the risk of outliers after domain adaptation and improves the model generalization capability. Extensive experiments show the superiority of our mixDA on several public glaucoma datasets. Moreover, our method outperforms state-of-the-art methods by a large margin on four glaucoma datasets: REFUGE, LAG, ORIGA, and RIM-ONE.

With the development of smart grids and the increasing demand for electric energy consumption, electricity load forecasting has become more and more important in electric energy management. However, the differences in electricity load patterns between different regions lead to data heterogeneity, which may seriously affect the model performance of traditional federated learning methods in electricity load forecasting. Meanwhile, the resource heterogeneity between clients will further decrease the efficiency and the accuracy of forecasting. To this end, we propose a spatio–temporal aware personalized federated learning (PFL) framework for electricity load forecasting to improve the forecasting accuracy and training speed so as to enhance the real-time responsiveness and system stability of the power grid. First, to solve the data heterogeneity, we design a collaborative training domain (CTD) construction method based on spatio–temporal features. Then, on the basis of constructed CTDs, we propose a spatio–temporal convolutional network (STCN)-based layered PFL method to address the resource heterogeneity, which can be divided into personalized layers and generalized layers according to temporal and spatial static features separately. In addition, we design a hierarchical aggregation mechanism and an adaptive edge model aggregation adjustment mechanism to optimize the training process. Experimental results show that the method proposed in this article outperforms other methods in terms of model accuracy and convergence speed.

False data injection attack (FDIA) can pose a severe threat to the distribution networks (DN), and the accurate detection of FDIA plays a key role in the safe and reliable operation of the DN. In this article, an end-edge-cloud collaboration-based detection framework is proposed to detect FDIA in the DN. First, in order to effectively preserve the privacy of different stakeholders in the DN and solve the problem of data island, a federated-learning-based edge-cloud collaboration mechanism is designed according to the proposed end-edge-cloud collaboration framework to jointly train the local FDIA detection models and eventually build a comprehensive FDIA detection model. Then, considering the temporal–spatial correlation of measurement data, a local data-driven FDIA detection model is proposed based on a novel temporal–spatial graph convolutional network, which can extract temporal–spatial features of the measurement data and improve the FDIA detection performance. In general, compared with the traditional centralized FDIA detection methods, the proposed method can make full use of the computational capacity of distributed edge devices and reduce the pressure of computation on the control center. Finally, simulation results based on the modified IEEE 14-bus and IEEE 118-bus distribution systems indicate that the proposed method can effectively improve the accuracy of FDIA detection compared with other methods.

The use of deep learning technology to manipulate images and videos of people in ways that are difficult to distinguish from the real ones, known as deepfake, has become a matter of national security concern in recent years. As a result, many studies have been carried out to detect deepfake and manipulated media. Among these studies, deep video models based on convolutional neural networks have been the preferred method for detecting deepfake in videos. This study presents a novel deep video model called Sequential-Parallel Networks (SPNet) that provides efficient deepfake detection. The SPNet model consists of a simple yet innovative sequential-parallel block that first extracts spatial and temporal features sequentially, then concatenates them together in parallel. As a result, the presented SPNet possesses comparable spatiotemporal modeling abilities as most state-of-the-art deep video methods but with lower computation complexity and fewer parameters. The efficiency of the presented SPNet is demonstrated on a large-scale deepfake benchmark in terms of high recognition accuracy and low computational cost.

In this study, we propose a novel approach to synthesize high-resolution and hyper-realistic face images with controlled attributes. Firstly, by training an attribute classifier to assign attribute labels to given synthesized face images, we build the links between latent vectors and face attributes. Secondly, we adapt the regression method to match the distributions of latent vectors with the corresponding face attributes, to control the attribute synthesis in the face images. Finally, we use the Gram-Schmidt orthogonalization algorithm to disentangle the attribute feature axes in latent space, such that a change in one attribute will not cause any changes in other attributes. Extensive experiments demonstrate the effectiveness of the proposed approach for high-quality face image synthesis with controlled attributes.

Protein-protein interactions (PPIs) are crucial in various biological processes and their study has significant implications for drug development and disease diagnosis. Existing deep learning methods suffer from significant performance degradation under complex real-world scenarios due to various factors, e.g., label scarcity and domain shift. In this paper, we propose a self-ensembling multi-graph neural network (SemiGNN-PPI) that can effectively predict PPIs while being both efficient and generalizable. In SemiGNN-PPI, we not only model the protein correlations but explore the label dependencies by constructing and processing multiple graphs from the perspectives of both features and labels in the graph learning process. We further marry GNN with Mean Teacher to effectively leverage unlabeled graph-structured PPI data for self-ensemble graph learning. We also design multiple graph consistency constraints to align the student and teacher graphs in the feature embedding space, enabling the student model to better learn from the teacher model by incorporating more relationships. Extensive experiments on PPI datasets of different scales with different evaluation settings demonstrate that SemiGNN-PPI outperforms state-of-the-art PPI prediction methods, particularly in challenging scenarios such as training with limited annotations and testing on unseen data.

Nowadays, increasing number of services are provided to individuals and organizations through cloud computing systems in apay-as-you-usemodel. This business service paradigm encounters several cloud Quality of Service (QoS) challenges, such as reliability, cost, and response time. The most common mechanism to improve cloud service reliability is a primary/backup (PB) fault-tolerant technique. However, this reliability enhancement technique inevitably results in multiple replications, which lead to high service cost. In recognition of these challenges, we first build a cloud computing systems resources management architecture. Then, we analyze the cloud service execution reliability on the physical resources of a VM and used a CUDA (Compute Unified Device Architecture)-enabled parallel two-dimensional long short-term memory neural network to predict the software faults of a cloud VM. Third, we propose an effective primary/backup cloud service cost calculation approach. To overcome the cloud service response time constraint, we integrate a response time slack factor into this method. Fourth, we formulate the cloud service reliability and cost aware job scheduling problem, which aims at minimizing the total cloud service cost and rejection rate, and improving the system reliability. Fifthly, a heuristic greedy reliability and cost aware job scheduling (RCJS) algorithm is proposed. Finally, a performance evaluation is conducted and the experimental results demonstrate that our proposed RCJS algorithm significantly outperforms optimal redundant VM placement (OPVMP), MIN-MIN algorithms in terms of average service cost and rejection rate. This algorithm also demonstrates good trade-off of reliability when compared to the other two algorithms and is suitable for cloud services with high reliability and low-cost requirements.

Analysis of high dimensional biomedical data such as microarray gene expression data and mass spectrometry images, is crucial to provide better medical services including cancer subtyping, protein homology detection, etc. Clustering is a fundamental cognitive task which aims to group unlabeled data into multiple clusters based on their intrinsic similarities. However, for most clustering methods, including the most widely used K-means algorithm, all features of the high dimensional data are considered equally in relevance, which distorts the performance when clustering high-dimensional data where there exist many redundant variables and correlated variables. In this paper, we aim at addressing the problem of the high dimensional bioinformatics data clustering and propose a new correlation induced clustering, CoIn, to capture complex correlations among high dimensional data and guarantee the correlation consistency within each cluster. We evaluate the proposed method on a high dimensional mass spectrometry dataset of liver cancer tumor to explore the metabolic differences on tissues and discover the intra-tumor heterogeneity (ITH). By comparing the results of baselines and ours, it has been found that our method produces more explainable and understandable results for clinical analysis, which demonstrates the proposed clustering paradigm has the potential with application to knowledge discovery in high dimensional bioinformatics data.

While deep learning methods hitherto have achieved considerable success in medical image segmentation, they are still hampered by two limitations: (i) reliance on large-scale well-labeled datasets, which are difficult to curate due to the expert-driven and time-consuming nature of pixel-level annotations in clinical practices, and (ii) failure to generalize from one domain to another, especially when the target domain is a different modality with severe domain shifts. Recent unsupervised domain adaptation (UDA) techniques leverage abundant labeled source data together with unlabeled target data to reduce the domain gap, but these methods degrade significantly with limited source annotations. In this study, we address this underexplored UDA problem, investigating a challenging but valuable realistic scenario, where the source domain not only exhibits domain shift w.r.t. the target domain but also suffers from label scarcity. In this regard, we propose a novel and generic framework called "Label-Efficient Unsupervised Domain Adaptation" (LE-UDA). In LE-UDA, we construct self-ensembling consistency for knowledge transfer between both domains, as well as a self-ensembling adversarial learning module to achieve better feature alignment for UDA. To assess the effectiveness of our method, we conduct extensive experiments on two different tasks for cross-modality segmentation between MRI and CT images. Experimental results demonstrate that the proposed LE-UDA can efficiently leverage limited source labels to improve cross-domain segmentation performance, outperforming state-of-the-art UDA approaches in the literature.

Cardiac magnetic resonance (CMR) imaging is frequently recommended for patients at intermediate risk of cardiovascular disease to triage them for medication or invasive aggressive treatment. Mitral annulus (MA) motion and velocities represent the cardiac contraction and relaxation, and hold potential to improve the detection of subtle cardiac dysfunction. However, conventional interpretation of CMR images requires expert manipulation and is often operator-dependent. In this paper, we propose an end-to-end MA Point Tracking Network (MANet) to automatically detect and track MA motion during cardiac cycle. The MANet model consists of MA point detection module and motion tracking module. In MA point detection, we design the convolutional-based feature extraction and elastic regression to detect MA points frame by frame of each CMR video. Then, in MA tracking, we adopt the Deep SORT model to capture spatio-temporal continuity between frames and fine-tune the coordinate position of MA points. 171 CMR videos with 4275 frames are used in comparison experiments, and the results demonstrate that our MANet model achieves promising performance in reference to clinical ground truth (r=0.71, P<0.001). This work provides an important preamble for cardiac motion tracking and cardiac function evaluation.

Recent advances in deep neural networks, especially in generative adversarial networks (GAN), have shown remarkable progress in face image generations. However, most of the existing face image generators can only synthesize random face images, but are not able to control the attributes of the generated face images. Though conditional GAN based methods can manipulate the attributes to some extent, but can only generate low-resolution face images up to 256 × 256. In this study, based on StyleGAN, one of the state-of-the-art image generators for synthesizing high-quality face images, we propose a simple but efficient approach to generate high-resolution and hyper-realistic face images with any desired attribute. By training an attribute classifier to assign attribute labels to given synthesized face images, we build the links between latent vectors and face attributes. In such a way, the latent vectors can be grouped into different clusters, one cluster corresponding to one face attribute, respectively. We then extract the prototypes for the clusters, which are used to control the attribute of the generated face image. Extensive experiments demonstrate the effectiveness of the proposed approach for high-quality face image generation with predefined attributes.

Multi-label Learning on image data has been widely exploited with deep learning models. However, supervised training on deep CNN models often cannot discover sufficient discriminative features for classification. As a result, numerous self-supervision methods are proposed to learn more robust image representations. However, most self-supervised approaches focus on single-instance single-label data and fall short on more complex images with multiple objects. Therefore, we propose an Object-Aware Self-Supervision (OASS) method to obtain more fine-grained representations for multi-label learning, dynamically generating auxiliary tasks based on object locations. Secondly, the robust representation learned by OASS can be leveraged to efficiently generate Class-Specific Instances (CSI) in a proposal-free fashion to better guide multi-label supervision signal transfer to instances. Extensive experiments on the VOC2012 dataset for multi-label classification demonstrate the effectiveness of the proposed method against the state-of-the-art counterparts.

Deep learning has achieved remarkable progress in computer vision and image analysis. However, raindrop removal from single image still remains challenging, due to a wide range of raindrop diversities and surface reflections. In this paper, we propose an iterative neural network with feedback strategy and contrastive learning for single image raindrop removal. First, we design an iterative feedback neural network to refine low-level representations with high-level information, i.e., the output of the previous iteration is used as input for the next iteration, together with the input image with raindrops. As a result, raindrops could be gradually removed through this feedback manner. Then, we deploy contrastive regularization to push the restored image from each iteration close to the clean images without raindrops, but away from rainy images with raindrops. Extensive experiments on two raindrop benchmark datasets demonstrate the effectiveness of the proposed approach in comparison with the state-of-the-art methods. The methodology in this work could be further extended to self-supervised contrastive learning to obtain robust feature representations with less labelled data.

With large-scale well-labeled datasets, deep learning has shown significant success in medical image segmentation. However, it is challenging to acquire abundant annotations in clinical practice due to extensive expertise requirements and costly labeling efforts. Recently, contrastive learning has shown a strong capacity for visual representation learning on unlabeled data, achieving impressive performance rivaling supervised learning in many domains. In this work, we propose a novel multi-scale multi-view global-local contrastive learning (MMGL) framework to thoroughly explore global and local features from different scales and views for robust contrastive learning performance, thereby improving segmentation performance with limited annotations. Extensive experiments on the MM-WHS dataset demonstrate the effectiveness of MMGL framework on semi-supervised cardiac image segmentation, outperforming the state-of-the-art contrastive learning methods by a large margin.

While deep models have shown promising performance in medical image segmentation, they heavily rely on a large amount of well-annotated data, which is difficult to access, especially in clinical practice. On the other hand, high-accuracy deep models usually come in large model sizes, limiting their employment in real scenarios. In this work, we propose a novel asymmetric co-teacher framework, ACT-Net, to alleviate the burden on both expensive annotations and computational costs for semi-supervised knowledge distillation. We advance teacher-student learning with a co-teacher network to facilitate asymmetric knowledge distillation from large models to small ones by alternating student and teacher roles, obtaining tiny but accurate models for clinical employment. To verify the effectiveness of our ACT-Net, we employ the ACDC dataset for cardiac substructure segmentation in our experiments. Extensive experimental results demonstrate that ACT-Net outperforms other knowledge distillation methods and achieves lossless segmentation performance with 250× fewer parameters.

Automated facial age estimation has diverse real-world applications in multimedia analysis, e.g., video surveillance, and human-computer interaction. However, due to the randomness and ambiguity of the aging process, age assessment is challenging. Most research work over the topic regards the task as one of age regression, classification, and ranking problems, and cannot well leverage age distribution in representing labels with age ambiguity. In this work, we propose a simple yet effective loss function for robust facial age estimation via distribution learning, i.e., adaptive mean-residue loss, in which, the mean loss penalizes the difference between the estimated age distribution's mean and the ground-truth age, whereas the residue loss penalizes the entropy of age probability out of dynamic top-K in the distribution. Experimental results in the datasets FG-NET and CLAP2016 have validated the effectiveness of the proposed loss.

Abstract Deep neural networks have achieved great success in both computer vision and natural language processing tasks. How to improve the gradient flows is crucial in training very deep neural networks. To address this challenge, a gradient enhancement approach is proposed through constructing the short circuit neural connections. The proposed short circuit is a unidirectional neural connection that back propagates the sensitivities rather than gradients in neural networks from the deep layers to the shallow layers. Moreover, the short circuit is further formulated as a gradient truncation operation in its connecting layers, which can be plugged into the backbone models without introducing extra training parameters. Extensive experiments demonstrate that the deep neural networks, with the help of short circuit connection, gain a large margin of improvement over the baselines on both computer vision and natural language processing tasks. The work provides the promising solution to the low‐resource scenarios, such as, intelligence transport systems of computer vision, question answering of natural language processing.

Recent graph neural network (GNN) based methods for few-shot learning (FSL) represent the samples of interest as a fully-connected graph and conduct reasoning on the nodes flatly, which ignores the hierarchical correlations among nodes. However, real-world categories may have hierarchical structures, and for FSL, it is important to extract the distinguishing features of the categories from individual samples. To explore this, we propose a novel hierarchical graph neural network (HGNN) for FSL, which consists of three parts, i.e., bottom-up reasoning, top-down reasoning, and skip connections, to enable the efficient learning of multi-level relationships. For the bottom-up reasoning, we design intra-class k-nearest neighbor pooling (intra-class knnPool) and inter-class knnPool layers, to conduct hierarchical learning for both the intra- and inter-class nodes. For the top-down reasoning, we propose to utilize graph unpooling (gUnpool) layers to restore the down-sampled graph into its original size. Skip connections are proposed to fuse multi-level features for the final node classification. The parameters of HGNN are learned by episodic training with the signal of node losses, which aims to train a well-generalizable model for recognizing unseen classes with few labeled data. Experimental results on benchmark datasets have demonstrated that HGNN outperforms other state-of-the-art GNN based methods significantly, for both transductive and non-transductive FSL tasks. The dataset as well as the source code can be downloaded online1

Deep learning methods are becoming the de-facto standard for generic visual recognition in the literature. However, their adaptations to industrial scenarios, such as visual recognition for machines, product streamlines, etc., which consist of countless components, have not been investigated well yet. Compared with the generic object detection, there is some strong structural knowledge in these scenarios (e.g., fixed relative positions of components, component relationships, etc.). A case worth exploring could be automated visual inspection for trains, where there are various correlated components. However, the dominant object detection paradigm is limited by treating the visual features of each object region separately without considering common sense knowledge among objects. In this article, we propose a novel automated visual inspection framework for trains exploring structural knowledge for train component detection, which is called SKTCD. SKTCD is an end-to-end trainable framework, in which the visual features of train components and structural knowledge (including hierarchical scene contexts and spatial-aware component relationships) are jointly exploited for train component detection. We propose novel residual multiple gated recurrent units (Res-MGRUs) that can optimally fuse the visual features of train components and messages from the structural knowledge in a weighted-recurrent way. In order to verify the feasibility of SKTCD, a dataset that contains high-resolution images captured from moving trains has been collected, in which 18 590 critical train components are manually annotated. Extensive experiments on this dataset and on the PASCAL VOC dataset have demonstrated that SKTCD outperforms the existing challenging baselines significantly. The dataset as well as the source code can be downloaded online (https://github.com/smartprobe/SKCD).

Traffic prediction based on massive speed data collected from traffic sensors plays an important role in traffic management. However, it is still challenging to obtain satisfactory performance due to the complex and dynamic spatial-temporal correlations among the data. Recently, many research works have demonstrated the effectiveness of graph neural networks (GNNs) for spatial-temporal modeling. However, such models are restricted by conditional distribution during training, and may not perform well when the target is outside the primary region of interest in the distribution. In this article, we address this problem with a stagewise learning mechanism, in which we redefine speed prediction as a conditional distribution learning followed by speed regression. We first perform a conditional distribution learning for each observed speed class, and then obtain speed prediction by optimizing regression learning, based on the learned conditional distribution. To effectively learn the conditional distribution, we introduce a mean-residue loss, consisting of two parts: 1) a mean loss, which penalizes the differences between the mean of the estimated conditional distribution and the ground truth and 2) a residue loss, which penalizes residue errors of the long tails in the distribution. To optimize the subsequent regression based on distribution information, we combine the mean absolute error (MAE) as another part of the loss function. We also incorporate a GNN-based architecture with our proposed learning mechanism. Mean-residue loss is employed to supervise the hidden speed representation in the network at each time interval, followed by a shared layer to recalibrate the hidden temporal dependencies in the conditional distribution. The experimental results based on three public traffic datasets have demonstrated that the effectiveness of the proposed method outperforms state-of-the-art methods.

Artificial intelligence shows promising efforts in collaborating the language models with the artificial intelligence of things (AIoT), promoting the edging intelligence on natural language understanding. To adapt to the limited computational resources in AIoT, the large language models (e.g., transformer) are compressed into light-weight models, which always results in poor feature representation and unsatisfactory performance on downstream tasks, especially on those low-resource language understanding tasks. To address the above issues, we propose a method named memory-assistant multi-task learning (MAMT), where an auxiliary memory module is introduced to promote multitask learning (MT), which serves as a surrogate of target domain representation and performs instance-level weighted MT. More importantly, our MAMT module is in a plug-and-play fashion. Thus, researchers can plug in it to conduct collaborative training and plug it out for AIoT model inference without extra computation burdens. Experiments demonstrate that MAMT significantly improves the performance of light-weight transformer models and show its superiority over the state-of-the-arts on eight GLUE subtasks.

Defect detection of trains is of great significance for operation safety and maintenance efficiency for railway maintenance. Nowadays, China railway system utilizes high-speed line scan cameras to capture images of critical parts of moving trains. The visual inspection on the images still heavily relies on manual interpretation. To reduce the labor requirements, we propose a novel two-stage deep learning based framework for component defect detection of moving trains. The proposed framework is composed of two major successive stages: detecting train components by using our proposed hierarchical object detection scheme (HOD), and detecting component defects based on multiple neural networks and image processing methods. Our proposed HOD can effectively detect and localize train components from large to small in a hierarchical way. Furthermore, a gated feature fusion method that can extract and combine the hierarchical contextual features and spatial contexts is also proposed to improve the performance. To the best of our knowledge, it is the first time in the literature that component defect detection of moving trains is systematically analyzed. Extensive experiments on real images from China railway system have demonstrated that our framework outperforms the state-of-the-art baselines significantly.

Early risk diagnosis and driving anomaly detection from vehicle stream are of great benefits in a range of advanced solutions towards Smart Road and crash prevention, although there are intrinsic challenges, especially lack of ground truth, definition of multiple risk exposures. This study proposes a domain-specific automatic clustering (termed AutoCluster) to self-learn the optimal models for unsupervised risk assessment, which integrates key steps of clustering into an auto-optimisable pipeline, including feature and algorithm selection, hyperparameter auto-tuning. Firstly, based on surrogate conflict measures, a series of risk indicator features are constructed to represent temporal-spatial and kinematical risk exposures. Then, we develop an unsupervised feature selection method to identify the useful features by elimination-based model reliance importance (EMRI). Secondly, we propose balanced Silhouette Index (bSI) to evaluate the internal quality of imbalanced clustering. A loss function is designed that considers the clustering performance in terms of internal quality, inter-cluster variation, and model stability. Thirdly, based on Bayesian optimisation, the algorithm auto-selection and hyperparameter auto-tuning are self-learned to generate the best clustering results. Herein, NGSIM vehicle trajectory data is used for test-bedding. Findings show that AutoCluster is reliable and promising to diagnose multiple distinct risk levels inherent to generalised driving behaviour. We also delve into risk clustering, such as, algorithms heterogeneity, Silhouette analysis, hierarchical clustering flows, etc. Meanwhile, the AutoCluster is also a method for unsupervised data labelling and indicator threshold calibration. Furthermore, AutoCluster is useful to tackle the challenges in imbalanced clustering without ground truth or a priori knowledge.

Time-series forecasting is an important problem across a wide range of domains. Designing accurate and prompt forecasting algorithms is a non-trivial task, as temporal data that arise in real applications often involve both non-linear dynamics and linear dependencies, and always have some mixtures of sequential and periodic patterns, such as daily, weekly repetitions, and so on. At this point, however, most recent deep models often use Recurrent Neural Networks (RNNs) to capture these temporal patterns, which is hard to parallelize and not fast enough for real-world applications especially when a huge amount of user requests are coming. Recently, CNNs have demonstrated significant advantages for sequence modeling tasks over the de-facto RNNs, while providing high computational efficiency due to the inherent parallelism. In this work, we propose HyDCNN, a novel hybrid framework based on fully Dilated CNN for time-series forecasting tasks. The core component in HyDCNN is a proposed hybrid module, in which our proposed position-aware dilated CNNs are utilized to capture the sequential non-linear dynamics and an autoregressive model is leveraged to capture the sequential linear dependencies. To further capture the periodic temporal patterns, a novel hop scheme is introduced in the hybrid module. HyDCNN is then composed of multiple hybrid modules to capture the sequential and periodic patterns. Each of these hybrid modules targets on either the sequential pattern or one kind of periodic patterns. Extensive experiments on five real-world datasets have shown that the proposed HyDCNN is better compared with state-of-the-art baselines and is at least 200% better than RNN baselines. The datasets and source code will be published in Github to facilitate more future work.

Recently, deep learning-based approaches have achieved superior performance on object detection applications. However, object detection for industrial scenarios, where the objects may also have some structures and the structured patterns are normally presented in a hierarchical way, is not well investigated yet. In this work, we propose a novel deep learning-based method, hierarchical graphical reasoning (HGR), which utilizes the hierarchical structures of trains for train component detection. HGR contains multiple graphical reasoning branches, each of which is utilized to conduct graphical reasoning for one cluster of train components based on their sizes. In each branch, the visual appearances and structures of train components are considered jointly with our proposed novel densely connected dual-gated recurrent units (Dense-DGRUs). To the best of our knowledge, HGR is the first kind of framework that explores hierarchical structures among objects for object detection. We have collected a data set of 1130 images captured from moving trains, in which 17 334 train components are manually annotated with bounding boxes. Based on this data set, we carry out extensive experiments that have demonstrated our proposed HGR outperforms the existing state-of-the-art baselines significantly. The data set and the source code can be downloaded online at https://github.com/ChengZY/HGR.

In recent years, more and more large-scale data processing and computing workflow applications run on heterogeneous clouds. Such cloud applications with precedence-constrained tasks are usually deadline-constrained and their scheduling is an essential problem faced by cloud providers. Moreover, minimizing the workflow execution cost based on cloud billing periods is also a complex and challenging problem for clouds. In realizing this, we first model the workflow applications as I/O Data-aware Directed Acyclic Graph (DDAG), according to clouds with global storage systems. Then, we mathematically state this deadline-constrained workflow scheduling problem with the goal of minimum execution financial cost. We also prove that the time complexity of this problem is NP-hard by deducing from a multidimensional multiple-choice knapsack problem. Third, we propose a heuristic cost-efficient task scheduling strategy called CETSS, which includes workflow DDAG model building, task subdeadline initialization, greedy workflow scheduling algorithm, and task adjusting method. The greedy workflow scheduling algorithm mainly consists of dynamical task renting billing period sharing method and unscheduled task subdeadline relax technique. We perform rigorous simulations on some synthetic randomly generated applications and real-world applications, such as Epigenomics, CyberShake, and LIGO. The experimental results clearly demonstrate that our proposed heuristic CETSS outperforms the existing algorithms and can effective save the total workflow execution cost. In particular, CETSS is very suitable for large workflow applications.

Recent research works have pointed out that the synthesized images by StyleGAN contain prominent circular artifacts which severely degrade the quality of generated images. In this work, we provide a systematic investigation on how those circular artifacts are formed by studying the functionalities of different modules that are used in the Style-GAN architecture. We present both analysis of the StyleGAN mechanism and extensive experiments to verify our claims. The key modules of StyleGAN that promote such undesired artifacts are highlighted based on the analysis. Besides, we propose a simple yet effective solution to remove the prominent circular artifacts for StyleGAN, by applying a simple but efficient pixel-instance normalization layer. The improved StyleGAN model trained via our proposed approach successfully prevents the appearance of circular artifacts in the generated images.

With the rapid development of edge computing, edge clusters need to deal with a tremendous amount of tasks, making some edge clusters overloaded, which further translates into task completion lag. Previous works usually copy the tasks from overloaded edges to idle edges so as to reduce the task queuing and computing delay. However, the completion delay of tasks copied to different edges cannot be predicted before the replication decision is made, which affects the overall task replication performance. In this paper, we propose an online task replication algorithm based on the predictions derived from multi-armed bandit. Via rigorous proof, the regret is ensured to be sub-linear upon the bandit, measuring the gap between the online decisions and the offline optimum. Extensive simulations are conducted to confirm the superiority of the proposed algorithm over state-of-the-art replication strategies.

Since the real-time video analytics with high accuracy requirement is resource-consuming, the profiles regarding such resource-accuracy trade-off are needed before the analytics for better resource allocation at resource-constrained edges. With the inner changes of the video contents, outdated profiles fail to capture the trade-off dynamically over time, which requires the profiles to be updated periodically and incurs an overwhelming resource overhead. Thus, we present Soudain, which dynamically adjusts the configurations in profiles and corresponding profiling intervals to capture the inner changes of multiple video streams at edges. Upon the fine-grained decisions for profiles, we propose an integer program to maximize the accuracy of video analytics in a long-term scope with resource constraint, and then design an algorithm to adjust the profiles in an online manner. We implement Soudain upon the server with GPU. Our testbed evaluations confirm that, by using the live video streams derived from real-world traffic cameras, Soudain ensures the real-time requirement and achieves up to 25% improvement on the detection accuracy, compared with multiple state-of-the-art alternatives.

Is recurrent network really necessary for learning a good visual representation for video based person re-identification (VPRe-id)? In this paper, we first show that the common practice of employing recurrent neural networks (RNNs) to aggregate temporal-spatial features may not be optimal. Specifically, with a diagnostic analysis, we show that the recurrent structure may not be effective learn temporal dependencies than what we expected and implicitly yields an orderless representation. Based on this observation, we then present a simple yet surprisingly powerful approach for VPRe-id, where we treat VPRe-id as an efficient orderless ensemble of image based person re-identification problem. More specifically, we divide videos into individual images and re-identify person with ensemble of image based rankers. Under the i.i.d. assumption, we provide an error bound that sheds light upon how could we improve VPRe-id. Our work also presents a promising way to bridge the gap between video and image based person re-identification. Comprehensive experimental evaluations demonstrate that the proposed solution achieves state-of-the-art performances on multiple widely used datasets (iLIDS-VID, PRID 2011, and MARS).

Nonlinear regression has been extensively employed in many computer vision problems (e.g., crowd counting, age estimation, affective computing). Under the umbrella of deep learning, two common solutions exist i) transforming nonlinear regression to a robust loss function which is jointly optimizable with the deep convolutional network, and ii) utilizing ensemble of deep networks. Although some improved performance is achieved, the former may be lacking due to the intrinsic limitation of choosing a single hypothesis and the latter may suffer from much larger computational complexity. To cope with those issues, we propose to regress via an efficient "divide and conquer" manner. The core of our approach is the generalization of negative correlation learning that has been shown, both theoretically and empirically, to work well for non-deep regression problems. Without extra parameters, the proposed method controls the bias-variance-covariance trade-off systematically and usually yields a deep regression ensemble where each base model is both "accurate" and "diversified." Moreover, we show that each sub-problem in the proposed method has less Rademacher Complexity and thus is easier to optimize. Extensive experiments on several diverse and challenging tasks including crowd counting, personality analysis, age estimation, and image super-resolution demonstrate the superiority over challenging baselines as well as the versatility of the proposed method. The source code and trained models are available on our project page: https://mmcheng.net/dncl/.

Reports on changes to the author information presented in the above named paper.

As a new generation of Public Bicycle-sharing Systems (PBS), the Dockless PBS (DL-PBS) is an important application of cyber-physical systems and intelligent transportation. How to use artificial intelligence to provide efficient bicycle dispatching solutions based on dynamic bicycle rental demand is an essential issue for DL-PBS. In this article, we propose MORL-BD, a dynamic bicycle dispatching algorithm based on multi-objective reinforcement learning to provide the optimal bicycle dispatching solution for DL-PBS. We model the DL-PBS system from the perspective of cyber-physical systems and use deep learning to predict the layout of bicycle parking spots and the dynamic demand of bicycle dispatching. We define the multi-route bicycle dispatching problem as a multi-objective optimization problem by considering the optimization objectives of dispatching costs, dispatch truck's initial load, workload balance among the trucks, and the dynamic balance of bicycle supply and demand. On this basis, the collaborative multi-route bicycle dispatching problem among multiple dispatch trucks is modeled as a multi-agent and multi-objective reinforcement learning model. All dispatch paths between parking spots are defined as state spaces, and the reciprocal of dispatching costs is defined as a reward. Each dispatch truck is equipped with an agent to learn the optimal dispatch path in the dynamic DL-PBS network. We create an elite list to store the Pareto optimal solutions of bicycle dispatch paths found in each action, and finally get the Pareto frontier. Experimental results on the actual DL-PBS show that compared with existing methods, MORL-BD can find a higher quality Pareto frontier with less execution time.

Recent trend focuses on using heterogeneous graph of things (HGoT) to represent things and their relations in the Internet of Things, thereby facilitating the applying of advanced learning frameworks, i.e., deep learning (DL). Nevertheless, this is a challenging task since the existing DL models are hard to accurately express the complex semantics and attributes for those heterogeneous nodes and links in HGoT. To address this issue, we develop attention-aware encoder-decoder graph neural networks for HGoT, termed as HGAED. Specifically, we utilize the attention-based separate-and-merge method to improve the accuracy, and leverage the encoder-decoder architecture for implementation. In the heart of HGAED, the separate-and-merge processes can be encapsulated into encoding and decoding blocks. Then, blocks are stacked for constructing an encoder-decoder architecture to jointly and hierarchically fuse heterogeneous structures and contents of nodes. Extensive experiments on three real-world datasets demonstrate the superior performance of HGAED over state-of-the-art baselines.

Benefiting from convenient cycling and flexible parking locations, the Dockless Public Bicycle-sharing (DL-PBS) network becomes increasingly popular in many countries. However, redundant and low-utility stations waste public urban space and maintenance costs of DL-PBS vendors. In this article, we propose a Bicycle Station Dynamic Planning (BSDP) system to dynamically provide the optimal bicycle station layout for the DL-PBS network. The BSDP system contains four modules: bicycle drop-off location clustering, bicycle-station graph modeling, bicycle-station location prediction, and bicycle-station layout recommendation. In the bicycle drop-off location clustering module, candidate bicycle stations are clustered from each spatio-temporal subset of the large-scale cycling trajectory records. In the bicycle-station graph modeling module, a weighted digraph model is built based on the clustering results and inferior stations with low station revenue and utility are filtered. Then, graph models across time periods are combined to create a graph sequence model. In the bicycle-station location prediction module, the GGNN model is used to train the graph sequence data and dynamically predict bicycle stations in the next period. In the bicycle-station layout recommendation module, the predicted bicycle stations are fine-tuned according to the government urban management plan, which ensures that the recommended station layout is conducive to city management, vendor revenue, and user convenience. Experiments on actual DL-PBS networks verify the effectiveness, accuracy, and feasibility of the proposed BSDP system.

Image segmentation is one of the most essential biomedical image processing problems for different imaging modalities, including microscopy and X-ray in the Internet-of-Medical-Things (IoMT) domain. However, annotating biomedical images is knowledge-driven, time-consuming, and labor-intensive, making it difficult to obtain abundant labels with limited costs. Active learning strategies come into ease the burden of human annotation, which queries only a subset of training data for annotation. Despite receiving attention, most of active learning methods still require huge computational costs and utilize unlabeled data inefficiently. They also tend to ignore the intermediate knowledge within networks. In this work, we propose a deep active semi-supervised learning framework, DSAL, combining active learning and semi-supervised learning strategies. In DSAL, a new criterion based on deep supervision mechanism is proposed to select informative samples with high uncertainties and low uncertainties for strong labelers and weak labelers respectively. The internal criterion leverages the disagreement of intermediate features within the deep learning network for active sample selection, which subsequently reduces the computational costs. We use the proposed criteria to select samples for strong and weak labelers to produce oracle labels and pseudo labels simultaneously at each active learning iteration in an ensemble learning manner, which can be examined with IoMT Platform. Extensive experiments on multiple medical image datasets demonstrate the superiority of the proposed method over state-of-the-art active learning methods.

Diabetes is one of the most common disease in individuals. Diabetic retinopathy (DR) is a complication of diabetes, which could lead to blindness. Automatic DR grading based on retinal images provides a great diagnostic and prognostic value for treatment planning. However, the subtle differences among severity levels make it difficult to capture important features using conventional methods. To alleviate the problems, a new deep learning architecture for robust DR grading is proposed, referred to as SEA-Net, in which, spatial attention and channel attention are alternatively carried out and boosted with each other, improving the classification performance. In addition, a hybrid loss function is proposed to further maximize the inter-class distance and reduce the intraclass variability. Experimental results have shown the effectiveness of the proposed architecture.

Deep Neural Network (DNN) has been applied widely nowadays, making remarkable achievements in a wide variety of research fields. With the improvement of the accuracy requirements for the inference results, the topology of DNN tends to be more and more complex, evolving from chain topology to directed acyclic graph (DAG) topology, which leads to the huge amount of computation. For those end devices which have limited computing resources, the delay of running DNN models independently may be intolerable. As a solution, edge computing can make use of all available devices in the edge computing environments comprehensively to run DNN inference tasks, so as to achieve the purpose of acceleration. In this case, how to split DNN inference task into several small tasks and assign them to different edge devices is the central issue. This paper proposes a load-balancing algorithm to split DNN with DAG topology adaptively according to the environment. Extensive experimental results show the the propose adaptive algorithm can effectively accelerate the inference speed.

Edge computing is one of the emerging technologies aiming to enable timely computation at the network edge. With virtualization technologies, the role of the traditional edge providers is separated into two: edge infrastructure providers (EIPs), who manage the physical edge infrastructure, and edge service providers (ESPs), who purchase slices of physical resources (e.g., CPU, bandwidth, memory space, disk storage) from EIPs and then cache service entities to offer their own value-added services to end users. These value-added services are also called virtual network function or VNF. As we know, edge computing environments are dynamic, and the requirements of edge service for computing resources usually fluctuate over time. Thus, when the demand of a VNF cannot be satisfied, we need to design the strategies for migrating the VNF so as to meet its demand and retain the network performance. In this paper, we concentrate on migrating VNFs efficiently (MV), such that the migration can meet the bandwidth requirement for data transmission. We prove that MV is NP-complete. We present several exact and heuristic solutions to tackle it. Extensive simulations demonstrate that the proposed heuristics are efficient and effective.

Traffic flow prediction is crucial for public safety and traffic management, and remains a big challenge because of many complicated factors, e.g., multiple spatio-temporal dependencies, holidays, and weather. Some work leveraged 2D convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) to explore spatial relations and temporal relations, respectively, which outperformed the classical approaches. However, it is hard for these work to model spatio-temporal relations jointly. To tackle this, some studies utilized LSTMs to connect high-level layers of CNNs, but left the spatio-temporal correlations not fully exploited in low-level layers. In this work, we propose novel spatio-temporal CNNs to extract spatio-temporal features simultaneously from low-level to high-level layers, and propose a novel gated scheme to control the spatio-temporal features that should be propagated through the hierarchy of layers. Based on these, we propose an end-to-end framework, multiple gated spatio-temporal CNNs (MGSTC), for citywide traffic flow prediction. MGSTC can explore multiple spatio-temporal dependencies through multiple gated spatio-temporal CNN branches, and combine the spatio-temporal features with external factors dynamically. Extensive experiments on two real traffic datasets demonstrates that MGSTC outperforms other state-of-the-art baselines.

Traffic prediction is of great importance to traffic management and public safety, and very challenging as it is affected by many complex factors, such as spatial dependency of complicated road networks and temporal dynamics, and many more. The factors make traffic prediction a challenging task due to the uncertainty and complexity of traffic states. In the literature, many research works have applied deep learning methods on traffic prediction problems combining convolutional neural networks (CNNs) with recurrent neural networks (RNNs), which CNNs are utilized for spatial dependency and RNNs for temporal dynamics. However, such combinations cannot capture the connectivity and globality of traffic networks. In this paper, we first propose to adopt residual recurrent graph neural networks (Res-RGNN) that can capture graph-based spatial dependencies and temporal dynamics jointly. Due to gradient vanishing, RNNs are hard to capture periodic temporal correlations. Hence, we further propose a novel hop scheme into Res-RGNN to utilize the periodic temporal dependencies. Based on Res-RGNN and hop Res-RGNN, we finally propose a novel end-to-end multiple Res-RGNNs framework, referred to as “MRes-RGNN”, for traffic prediction. Experimental results on two traffic datasets have demonstrated that the proposed MRes-RGNN outperforms state-of-the-art methods significantly.

Spatial modulation is a promising transmission scheme for massive multiple‐input multiple‐output (MIMO) systems to improve energy efficiency. In this study, considering the low‐complexity hybrid structure, the authors propose a joint spatial modulation and beamforming scheme for a hybrid massive MIMO system in both single user and multi‐user scenarios. Specifically, a design criterion of the channel control parameter is provided to reduce the high correlation among different channel coefficients in the hybrid massive MIMO system. In addition, with the statistical channel state information acquired at the base station, the optimum analogue beamforming vectors are designed with the goal of maximising the signal to leakage and noise ratio in the multi‐user scenario. Furthermore, the upper bound, the lower bound as well as the closed form approximation of achievable spectral efficiency of the proposed scheme are derived for both single user and multi‐user scenarios. Numerical simulation results demonstrate that the proposed scheme outperforms the conventional MIMO scheme.

Predicting vehicle flows is of great importance to traffic management and public safety in smart cities, and very challenging as it is affected by many complex factors, such as spatio-temporal dependencies with external factors (e.g., holidays, events and weather). Recently, deep learning has shown remarkable performance on traditional challenging tasks, such as image classification, due to its powerful feature learning capabilities. Some works have utilized LSTMs to connect the high-level layers of 2D convolutional neural networks (CNNs) to learn the spatio-temporal features, and have shown better performance as compared to many classical methods in traffic prediction. However, these works only build temporal connections on the high-level features at the top layer while leaving the spatio-temporal correlations in the low-level layers not fully exploited. In this paper, we propose to apply 3D CNNs to learn the spatio-temporal correlation features jointly from low-level to high-level layers for traffic data. We also design an end-to-end structure, named as MST3D, especially for vehicle flow prediction. MST3D can learn spatial and multiple temporal dependencies jointly by multiple 3D CNNs, combine the learned features with external factors and assign different weights to different branches dynamically. To the best of our knowledge, it is the first framework that utilizes 3D CNNs for traffic prediction. Experiments on two vehicle flow datasets Beijing and New York City have demonstrated that the proposed framework, MST3D, outperforms the state-of-the-art methods.

In past years, deep convolutional neural networks (DCNN) have achieved big successes in image classification and object detection, as demonstrated on ImageNet in academic field. However, There are some unique practical challenges remain for real-world image recognition applications, e.g., small size of the objects, imbalanced data distributions, limited labeled data samples, etc. In this work, we are making efforts to deal with these challenges through a computational framework by incorporating latest developments in deep learning. In terms of two-stage detection scheme, pseudo labeling, data augmentation, cross-validation and ensemble learning, the proposed framework aims to achieve better performances for practical image recognition applications as compared to using standard deep learning methods. The proposed framework has recently been deployed as the key kernel for several image recognition competitions organized by Kaggle. The performance is promising as our final private scores were ranked 4 out of 2293 teams for fish recognition on the challenge "The Nature Conservancy Fisheries Monitoring" and 3 out of 834 teams for cervix recognition on the challenge "Intel &MobileODT Cervical Cancer Screening", and several others. We believe that by sharing the solutions, we can further promote the applications of deep learning techniques.

The increasing main memory capacity and the explosion of big data have fueled the development of in-memory big data management and processing. By offering an efficient in-memory parallel execution model which can eliminate disk I/O bottleneck, existing in-memory cluster computing platforms (e.g., Flink and Spark) have already been proven to be outstanding platforms for big data processing. However, these platforms are merely CPU-based systems. This paper proposes GFlink, an in-memory computing architecture on heterogeneous CPU-GPU clusters for big data. Our proposed architecture extends the original Flink from CPU clusters to heterogeneous CPU-GPU clusters, greatly improving the computational power of Flink. Furthermore, we have proposed a programming framework based on Flink's abstract model, i.e., DataSet (DST), hiding the programming complexity of GPUs behind the simple and familiar high-level interfaces. To achieve high performance and good load-balance, an efficient JVM-GPU communication strategy, a GPU cache scheme, and an adaptive locality-aware scheduling scheme for three-stage pipelining execution are proposed. Extensive experiment results indicate that the high computational power of GPUs can be efficiently utilized, and the implementation on GFlink outperforms that on the original CPU-based Flink.

Nowadays, more and more online services based on cloud computing have taken the places of some traditional applications (e.g., Health Care) that continuously generate large volume of data and require data storage and analysis in time. Such applications can be categorized as “Continuous Writing Applications” (CWA) that have particular requirements on bandwidth, storage, computation, and service reliability. In the meanwhile, they are very sensitive to the cost. In this paper, we present an architecture of multiple cloud service providers (CSPs) or “Cloud-of-Clouds” to provide services to the CWA and propose a novel resource scheduling algorithm to minimize the cost of entire systems. Difference from many research efforts that focus on a single resource, we take many factors into considerations that include user's requirements of bandwidth, storage and computation, the resources of CSPs that can provide, CSPs for data backup, the configurations of Cloud-of-Clouds, system models of CSPs, and many more. We first present the system models of classic CWA applications to capture the resource requirements of users on Cloud-of-Clouds. We then present the problem formulation and our optimal strategy of user scheduling based on Minimum First Derivative Length (MFDL) of load paths among the systems. Through theoretical analysis, we prove that our proposed algorithm Optimal user Scheduling for Cloud-of-Clouds (OSCC) can achieve the optimal solution.

This work conducts a feasibility study of deep learning approaches for automatic segmentation of left ventricle (LV) cavity from cardiac magnetic resonance (CMR) images. Automatic LV cavity segmentation is a challenging task, partially due to the small size of the object as compared to the large CMR image background, especially at the apex. To cater for small object segmentation, the authors present a localisation‐segmentation framework, to first locate the object in the large full image, then segment the object within the small cropped region of interest. The localisation is performed by a deep regression model based on convolutional neural networks, while the segmentation is done by the deep neural networks based on U‐Net architecture. They also employ the Dice loss function for the training process of the segmentation models, to investigate its effects on the segmentation performance. The deep learning models are trained and evaluated by using public endocardium‐annotated CMR datasets from York University and MICCAI 2009 LV Challenge websites. The average dice metric values of the authors’ proposed framework are 0.91 and 0.93, respectively, on these two databases. These results are promising as compared to the best results achieved by the current state‐of‐art, which shows the potentials of deep learning approaches for this particular application.

As time-triggered communication protocols [e.g., time-triggered controller area network (TTCAN), time-triggered protocol (TTP), and FlexRay] are widely used on vehicles, the scheduling of tasks and messages on in-vehicle networks becomes a critical issue for offering quality-of-service (QoS) guarantees to time-critical applications on vehicles. This paper studies a holistic scheduling problem for handling real-time applications in time-triggered in-vehicle networks where practical aspects in system design and integration are captured. The contributions of this paper are multifold. First, it designs a novel scheduling algorithm, referred to asUnfixed Start Time(UST) algorithm, which schedules tasks and messages in a flexible way to enhance schedulability. In addition, to tolerate assignment conflicts and further improve schedulability, it proposes two rescheduling and backtracking methods, namely,Rescheduling with Offset Modification(ROM) andBacktracking and Priority Promotion(BPP) procedures. Extensive performance evaluation studies are conducted to quantify the performance of the proposed algorithm under a variety of scenarios.

This paper presents a resonant-sensor interface that operates based on transient measurement of the resonator's exponential decay after a brief excitation at a frequency close to its resonance frequency. In contrast with oscillator-based interfaces, the presented readout circuit is capable of detecting the resonator's quality factor (Q) in addition to its resonance frequency, and can be used in the presence of large parasitic capacitors. A prototype of the interface's front-end circuit has been integrated in 0.35μm CMOS technology, and consumes only 36μA from a 3.3V supply during a measurement time of 2ms. Measurement results on a clamped-clamped beam resonator obtained using this prototype are in good agreement with results obtained using impedance analysis.

In the recent past, security-sensitive applications, such as electronic transaction processing systems, stock quote update systems, which require high quality of security to guarantee authentication, integrity, and confidentiality of information, have adopted heterogeneous distributed system (HDS) as their platforms. This is primarily due to the fact that single parallel-architecture-based systems may not be sufficient to exploit the available parallelism with the running applications. Most security-aware applications end up in handling dependence tasks, also referred to as Directed Acyclic Graph (DAG), on these HDSs. Unfortunately, most existing algorithms for scheduling such DAGs in HDS fail to fully consider security requirements. In this paper, we systematically design a security-driven scheduling architecture that can dynamically measure the trust level of each node in the system by using differential equations. To do so, we introduce task priority rank to estimate security overhead of such security-critical tasks. Furthermore, we propose a security-driven scheduling algorithm for DAGs which can achieve high quality of security for applications. Our rigorous performance evaluation study results clearly demonstrate that our proposed algorithm outperforms the existing scheduling algorithms in terms of minimizing the makespan, risk probability, and speedup. We also observe that the improvement obtained by our algorithm increases as the security-sensitive data of applications increases.

Server-side Web caching is an important technique used to reduce the user perceived latency (UPL). In large-scale multimedia systems, there are many Web proxies, connected with a multimedia server, that can cache some most popular multimedia objects. Multimedia objects have some particular characteristics, e.g., strict QoS requirements. Hence, even some efficient conventional caching strategies based on cache hit ratio, meant for non-multimedia objects, will confront some problems in dealing with the multimedia objects. If we consider additional resources of proxy besides cache space, say bandwidth, we can readily observe that high hit ratio may deteriorate the entire system performance. In this paper, we propose a novel placement model for networked multimedia systems, referred to as Hk/T model, which considers the combined influence of arrival rate, size, and playback time to select the objects to be cached. Based on this model, we propose an innovative Web cache replacement algorithm, named as ART-greedy algorithm, which can balance the load among the proxies and achieve a minimum average response time (ART) of the requests. Using an event-driven simulation, we evaluate the performance of our proposed algorithm under several situations. Our experimental results conclusively demonstrate that ART-greedy algorithm outperforms the most popular and commonly used LFU (least frequently used) algorithm significantly.

In a large-scale multimedia storage system (LMSS) where client requests for different multimedia objects may have different demands, placement and replication of the objects is an important factor, as it may result in an imbalance in server loading across the system. Since replica management and load balancing is all the more a crucial issue in multimedia systems, in the literature this problem is handled by centralized servers. Each object storage server (OSS) responses the requests coming from the centralized servers independently and has no communication with other OSSs among the system. In this paper, we design a novel distributed load balancing strategy of LMSS, in which the OSSs can cooperate together to achieve a high performance. Such OSS modeled as an M/M/m system, can replicate the objects to and balance the requests among other servers to achieve an optimal average waiting time (AWT) of the requests in the system. We validate the performance of the system via rigorous simulations with respect to several influencing factors and prove that our proposed strategy is scalable, flexible and efficient for the real-life applications.

In distributed multimedia storage systems where client requests for different multimedia objects may have different demands, placement and replication of the objects is an important factor, as it may result in an imbalance in server loading across the system. Replica management and load balancing is all the more a crucial issue for large-scale multimedia systems. We design and analyze a heuristic static strategy to determine the placement, number of replicas of the objects, and balance the client requests among the servers, to minimize the average waiting time (AWT) of the requests. Our strategy exploits clever virtual routing technique to strike a balance among the servers for load balancing. We validate the performance via rigorous simulations with respect to several influencing factors and compare with a system that uses hashing function only for load balancing.

In this paper, we classify the dynamic distributed load balancing algorithms for heterogenous distributed computer systems into three policies: queue adjustment policy (QAP), rate adjustment policy (RAP), and queue and rate adjustment policy (QRAP). We propose two efficient algorithms, referred to as rate-based load balancing via virtual routing (RLBVR) and queue-based load balancing via virtual routing (QLBVR), which belong to the above RAP and QRAP policies, respectively. We also consider algorithms estimated load information scheduling algorithm (ELISA) and perfect information algorithm, which were introduced in the literature, to implement QAP policy. Our focus is to analyze and understand the behaviors of these algorithms in terms of their load balancing abilities under varying load conditions (light, moderate, or high) and the minimization of the mean response time of jobs. We compare the above classes of algorithms by a number of rigorous simulation experiments to elicit their behaviors under some influencing parameters, such as load on the system and status exchange intervals. We also extend our experimental verification to large scale cluster systems such as a mesh architecture, which is widely used in real-life situations. From these experiments, recommendations are drawn to prescribe the suitability of the algorithms under various situations