The sensor streams influence and correlate with each other, and the hidden correlation can be used to identify and explain abnormal problems. This paper proposed one kind of anomaly detection service based on lag-correlation analysis. It first constructs correlation graph model based on lag-correlation analysis of multiple sensor streams. Then sensor streams groups are constructed according to the correlation degree in the graph model, and are encapsulated as corresponding services to realize the anomaly detection within and out of stream groups in real time. Experimental results on a real industrial sensor data set show that the proposed method is effective in anomaly detection tasks in multiple sensor stream data.

Abstract Adversarial attack for time-series classification model is widely explored and many attack methods are proposed. But there is not a method of attack based on the data itself. In this paper, we innovatively proposed a black-box sparse attack method based on data location. Our method directly attack the sensitive points in the time-series data according to statistical features extract from the dataset. At first, we have validated the transferability of sensitive points among DNNs with different structures. Secondly, we use the statistical features extract from the dataset and the sensitive rate of each point as the training set to train the predictive model. Then, predicting the sensitive rate of test set by predictive model. Finally, perturbing according to the sensitive rate. The attack is limited by constraining the L0 norm to achieve one-point attack. We conduct experiments on several datasets to validate the effectiveness of this method.

Abstract Workflow management system (WfMS) in cloud always works as platform as a service to manage customized business processes for massive enterprises. In big data era, non‐functional guarantees of such systems are significant when facing a large number of users and concurrent requests. It is not trivial to support multi‐tenancy and hold high‐availability, because traditional architecture cannot simultaneously satisfy requirements about data isolation and runtime efficiency. In this paper, a modularized distributed workflow management system is proposed, which considers both multi‐tenancy and high‐availability in storage and engine parts of the system. A multiple‐worker‐with‐separate‐schema mechanism is defined to jointly manage the data for tenants, and a proactive strategy is presented to intelligently dispatch large concurrent requests from users to engine workers. After extensive case studies and experiments in practical scenes, our system deployed on modest machines is proved to support tens of thousands of tenants, second‐level response time for 10 K concurrency, and no‐human‐intervened failure recovery for a fail‐stop system node.

Information extraction and its service is a hot topic. Many works focus on extracting information from a certain web page and ignore the localization of the webpage which contains useful information. Nevertheless, developing a holistic system to extract information consists of locating a webpage and extracting information from that webpage, and these two steps are indispensable. For instance, extracting lecture news from universities' websites is a typical hard task that need to locate web pages and extract news information from them. Due to different layouts and visual appearances, statistic-based methods and visual based methods failed to find them. In this study, we propose an all-holistic method to locate lecture news on the university website. Graph Convolutional Network (GCN) is applied to fuse the multimodal data, which could learn useful features from different views, the linked relationship, the visual similarity, and the semantic of web pages. Firstly, we apply the link model to explore the parent-child relationship between web pages, then calculate the similarity of parent-child pages using a visual model and obtain the semantic features based on the BERT model. Specifically, the visual similarity features are learned based on triplet loss function which imposes the Convolutional Neural Network (CNN) model to learn similar parts in the same group. Lastly, these features are fused into the GCN model to find a certain webpage and it can be adaptive to various university websites. The experiments conducted on 50 websites show our method outperforms state-of-the-art.

With the rapid growth of internet usage for enterprise-wide and cross-enterprise business applications (such as those in Electronic Commerce), workflow systems are gaining importance as an infrastructure for automating inter-organizational interactions. However, the traditional centralized workflow management technology can no longer meet the needs of current application services. For example, in e-commerce, cross-enterprise business applications may cause many security problems and cross-domain problems in the implementation of workflow. At the same time, due to the uncertainty and variability of environment and user requirements in practical applications, many business logics are difficult to be completely defined in advance. Therefore workflow models need to be immediately built or adjusted dynamically. Nowadays, distributed scheduling and decentralized control of workflow have become the emerging trend and are facing many challenges at the forefront of Internet development technology. In this paper, a distributed workflow control execution method based on “meta-process” is proposed. Specifically, we designed and implemented a decentralized distributed scheduling management system for workflow tasks. To manage and control the distributed scheduling of workflow, we constructed a “meta-process”, which can ensure the integrity of the control chain in the distributed scheduling process. Our system can efficiently handle the data state migration between task nodes and supports the dynamic adjustment of the workflow model. For validation, we simulated a large number of service scheme samples and applied them to the system, which proved that all service cases can be executed correctly. Therefore, the feasibility of this method is verified.

In the cloud computing environment, the release and dynamic deployment of microservices face many challenges, and the services' dependency is an important consideration for service deployment. The service call chain logs record rich information, such as the time and delay of each service call in the business tracking process, and present the logs in the form of a call chain. Existing research does not fully consider the local composite service dependencies and their discontinuous dependencies in the service chain. In order to obtain these complex dependencies and provide basic supporting data for the dynamic deployment and adjustment of microservices, a dependency model of microservices is proposed, and a dependency mining method based on call chain logs is designed to extract local dependencies and the discontinuous dependency relationship. The effectiveness of the algorithm is verified by testing on Alibaba Cloud Computing's public data set.

Business process model and notation BPMN2.0 is an industry standard in the field of business process management. In order not to destroy the association rules between the various tasks of the business process, and to schedule them in the cloud edge environment, improve the service quality of the business process, this paper proposes a method of segmentation and reconstruction of the BPMN2.0 model, based on the BMPN2.0 model of the original business process and its constraints of the cloud-edge environment, the original business process is divided and reconstructed into multiple sub-business processes, so that the reconstructed sub-business process conforms to the BPMN2.0 modeling standard and is actually usable, providing basis for the scheduling of business processes in the cloud-edge environment. Through example verification and experimental analysis, the effectiveness of the segmentation reconstruction method in this paper is verified.

In this paper, we describe PACOL (Panoramic-Collaboration), a decentralized and multi-layered architecture of runtime environment for service collaboration. We illustrate by a case study why it is designed as a decentralized control architecture, and why it is designed to support multi-tenants and service solution evolution and continuous optimization. Preliminary case analysis indicates that PACOL could be a feasible proposition to realise cross-domain, reliable and optimized service collaboration for service collaboration towards Internet of Services.

Information service is always a hot topic especially when the Web is accessible anywhere. In university, lecture information is very important for students and teachers who want to take part in academic meetings. Therefore, lecture news extraction is an important and imperative task. Many open information extraction methods have been proposed, but due to the high heterogeneity of websites, this task is still a challenge. In this paper, we propose a method based on fusing multiple features to locate lecture news on the university website. These features include the linked relationship between parent webpage and child webpages, the visual similarity, and the semantics of webpages. Additionally, this paper provides an information service based on a main content extraction algorithm for extracting the lecture information. Stable and invariant features enable the proposed method to adapt to various kinds of campus websites. The experiments conducted on 50 websites show the effectiveness and efficiency of the provided service.

Nowadays, an Internet of Things (IoT) device consists of algorithms, datasets, and models. Due to good performance of deep learning methods, many devices integrated well-trained models in them. IoT empowers users to communicate and control physical devices to achieve vital information. However, these models are vulnerable to adversarial attacks, which largely bring potential risks to the normal application of deep learning methods. For instance, very little changes even one point in the IoT time-series data could lead to unreliable or wrong decisions. Moreover, these changes could be deliberately generated by following an adversarial attack strategy. We propose a robust IoT data classification model based on an encode-decode joint training model. Furthermore, thermometer encoding is taken as a nonlinear transformation to the original training examples that are used to reconstruct original time series examples through the encode-decode model. The trained ResNet model based on reconstruction examples is more robust to the adversarial attack. Experiments show that the trained model can successfully resist to fast gradient sign method attack to some extent and improve the security of the time series data classification model.

Anomaly detection algorithms (ADA) have been widely used as services in many maintenance monitoring platforms. However, there are numerous algorithms that could be applied to these fast changing stream data. Furthermore, in IoT stream data due to its dynamic nature, the phenomena of conception drift happened. Therefore, it is a challenging task to choose a suitable anomaly detection service (ADS) in real time. For accurate online anomalous data detection, this paper developed a service selection method to select and configure ADS at run-time. Initially, a time-series feature extractor (Tsfresh) and a genetic algorithm-based feature selection method are applied to swiftly extract dominant features which act as representation for the stream data patterns. Additionally, stream data and various efficient algorithms are collected as our historical data. A fast classification model based on XGBoost is trained to record stream data features to detect appropriate ADS dynamically at run-time. These methods help to choose suitable service and their respective configuration based on the patterns of stream data. The features used to describe and reflect time-series data’s intrinsic characteristics are the main success factor in our framework. Consequently, experiments are conducted to evaluate the effectiveness of features closed by genetic algorithm. Experimentations on both artificial and real datasets demonstrate that the accuracy of our proposed method outperforms various advanced approaches and can choose appropriate service in different scenarios efficiently.

Many anomaly detection algorithms have been provided as services for more convenient and efficient utilization in IoT era. Due to concept drift existed in dynamic IoT stream data, it is a changeling task to apply proper anomaly detection services at run time. For effective on-line anomalous data discovery, this paper proposes a service selection framework to dynamically select and configure anomaly detection services. A fast classification model based on XGBoost is trained to identify the pattern of various stream data, so that suitable service can be selected and configured according to the pattern of stream data. Extensive experiments on real and synthetic data sets show that our framework can select suitable service for different scenarios, and the accuracy of the chosen services outperforms state-of-the-art methods.

Information service is always a hot topic especially when web is accessible anywhere. In university, lecture information is very import for students and teachers who want to take part in academic meetings. Therefore, lecture news extraction is an important and imperative task. Although many open information extraction methods have been proposed, but due to the highly heterogeneity of website, this task is still a challenge. In this manuscript, we propose a method based on fusing multiple features to locate lecture news in university web site. These features including the organization structure of lecture news catalog webpage, the visual similarity and the semantic of webpage. Additionally, this paper provide an information service based on a main content extraction algorithm for extracting lecture information. The stable and invariant features enable the propose method could adaptive to many kinds of campus website. The experiments conducted on 50 websites show the effectiveness and efficiencies of provided service.

Most of Traditional Chinese Medicine (TCM) data and ancient records exist in the form of books. The unstructured medical information is the foundation for building TCM knowledge service. The existing methods are not accurate enough to solve TCM named entity recognition and require a lot of manual labeling data. This paper proposes a semi-supervised embedded Semi-BERT-BiLSTM-CRF model. Based on the book “Diagnosis of Traditional Chinese Medicine in Traditional Chinese Medicine”, we select the physical features from the cleaned-up text information according to the characteristics of Chinese medicine classics, and then use a small amount of labeled data to train the BERT-BiLSTM-CRF model. The obtained model is used to predict unlabeled data and obtain pseudo-label data. The pseudo-label and labeled data are used as a training set for model training. Experiments show that TCM entity recognition accuracy of this method reaches 81.24%, which effectively improves the TCM entity recognition accuracy and reduces the manual labeling work. The results of this research can be applied to scenarios such as auxiliary diagnosis of TCM and expert system after subsequent improvement and transformation.

Borehole lithology discrimination is the foundation for formation evaluation and reservoir characterization. Due to the limitation of costing or accuracy, direct discrimination methods, such as borehole core and drilling cutting analysis, are unable to widely apply, while logging lithology interpretation provides an alternative solution for this task. To mitigate the influence of subjective bias, several machine learning algorithms, such as neural network, support vector machine, decision tree, and random forest (RF), have already been applied for logging lithology interpretation. However, the vast majority of preceding studies are simple applications that directly apply classification algorithms to the raw input space formed by logging curve values, only limited studies involved feature extraction or learning space transformation. In this letter, we propose a hybrid algorithm that combines the mean-shift algorithm and the RF algorithm for borehole lithology discrimination in the prototype similarity space. Experiments on data collected from nine different areas demonstrate that the proposed algorithm has significant advantages in accuracy compared with other algorithms, which provides a considerable alternative way for further machine learning-assisted logging lithology interpretation.