No abstract

With the increasing population of Industry 4.0, industrial big data (IBD) has become a hotly discussed topic in digital and intelligent industry field. The security problem existing in the signal processing on large scale of data stream is still a challenge issue in industrial internet of things, especially when dealing with the high-dimensional anomaly detection for intelligent industrial application. In this article, to mitigate the inconsistency between dimensionality reduction and feature retention in imbalanced IBD, we propose a variational long short-term memory (VLSTM) learning model for intelligent anomaly detection based on reconstructed feature representation. An encoder-decoder neural network associated with a variational reparameterization scheme is designed to learn the low-dimensional feature representation from high-dimensional raw data. Three loss functions are defined and quantified to constrain the reconstructed hidden variable into a more explicit and meaningful form. A lightweight estimation network is then fed with the refined feature representation to identify anomalies in IBD. Experiments using a public IBD dataset named UNSW-NB15 demonstrate that the proposed VLSTM model can efficiently cope with imbalance and highdimensional issues, and significantly improve the accuracy and reduce the false rate in anomaly detection for IBD according to F1, area under curve (AUC), and false alarm rate (FAR).

Along with the advancement of several emerging computing paradigms and technologies, such as cloud computing, mobile computing, artificial intelligence, and big data, Internet of Things (IoT) technologies have been applied in a variety of fields. In particular, the Internet of Healthcare Things (IoHT) is becoming increasingly important in Human Activity Recognition (HAR), due to the rapid development of wearable and mobile devices. In this study, we focus on the deep learning enhanced HAR in IoHT environments. A semi-supervised deep learning framework is designed and built for more accurate HAR, which efficiently use and analyze the weakly labeled sensor data to train the classifier learning model. To better solve the problem of inadequately labeled sample, an intelligent auto-labeling scheme based on Deep Q-Network (DQN) is developed with a newly designed distance-based reward rule, which can improve the learning efficiency in IoT environments. A multi-sensor based data fusion mechanism is then developed to seamlessly integrate the onbody sensor data, context sensor data, and personal profile data together, and a Long Short Term Memory (LSTM)-based classification method is proposed to identify fine-grained patterns according to the high-level features contextually extracted from sequential motion data. Finally, experiments and evaluations are conducted to demonstrate the usefulness and effectiveness of the proposed method using real world data.

Scholarly big data, which is a large scale collection of academic information, technical data, and collaboration relationships, has attracted increasing attentions, ranging from industries to academic societies. The widespread adoption of social computing paradigm has made it easier for researchers to join collaborative research activities, and share the academic data more extensively than ever before across the highly interlaced academic networks. In this study, we focus on the academic influence aware and multidimensional network analysis based on the integration of multi-source scholarly big data. Following three basic relations: Researcher-Researcher, Researcher-Article, and Article-Article, a set of measures is introduced and defined to quantify correlations in terms of activity-based collaboration relationship, specialty-aware connection, and topic-aware citation fitness among a series of academic entities (e.g., researchers and articles) within a constructed multidimensional network model. An improved Random Walk with Restart (RWR) based algorithm is developed, in which the time-varying academic influence is newly defined and measured in a certain social context, to provide researchers with research collaboration navigation for their future works. Experiments and evaluations are conducted to demonstrate the practicability and usefulness of our proposed method in scholarly big data analysisusing DBLP and ResearchGate data.

With the increasing population of Industry 4.0, both AI and smart techniques have been applied and become hotly discussed topics in industrial Cyber-Physical Systems (CPS). Intelligent anomaly detection for identifying cyber/physical attacks to guarantee the work efficiency and safety is still a challenging issue, especially when dealing with few labeled data for cyber-physical security protection. In this study, we propose a Few-Shot Learning model with Siamese Convolution Neural Network (FSL-SCNN), to alleviate the over-fitting issue and enhance the accuracy for intelligent anomaly detection in industrial CPS. A Siamese CNN encoding network is constructed to measure distances of input samples based on their optimized feature representations. A robust cost function design including three specific losses is then proposed to enhance the efficiency of training process. An intelligent anomaly detection algorithm is developed finally. Experiment results based on a fully labeled public dataset and a few labeled dataset demonstrate that our proposed FSL-SCNN can significantly improve False Alarm Rate (FAR) and F1 scores when detecting intrusion signals for industrial CPS security protection.

No abstract

No abstract

Recently, along with several technological advancements in Cyber-Physical Systems (CPS), the revolution of Industry 4.0 has brought in an emerging concept named Digital Twin (DT), which shows it potential to break the barrier between the physical and cyber space in smart manufacturing. However, it is still difficult to analyze and estimate the real-time structural and environmental parameters in terms of their dynamic changes in digital twinning, especially when facing detection tasks of multiple small objects from a large-scale scene with complex contexts in modern manufacturing environments. In this study, we focus on a small object detection model for DT (SOD-DT), aiming to realize the dynamic synchronization between a physical manufacturing system and its virtual representation. Three significant elements, including equipment, product, and operator, are considered as the basic environmental parameters to represent and estimate the dynamic characteristics and real-time changes in building a generic DT system of smart manufacturing workshop. A hybrid deep neural network model based on the integration of MobileNetv2, YOLOv4, and Openpose, is constructed to identify the real-time status from physical manufacturing environment to virtual space. A learning algorithm is then developed to realize the efficient multi-type small object detection based on the feature integration and fusion from both shallow and deep layers, in order to facilitate the modeling, monitoring, and optimizing of the whole manufacturing process in DT system. Experiments and evaluations conducted in