In this study, we consider surfacing control problems for the autonomous underwater vehicle in three-dimensional space under emergencies. Most model-based controllers cannot effectively solve these problems due to the unknown task environment model. Moreover, existing deep reinforcement learning (DRL) methods have some limitations, such as slow convergence or overestimation bias. For these purposes, we propose a model-free DRL algorithm based on the Deep Deterministic Policy Gradient within the paradigm of deep learning as a service (DLaaS). The algorithm combines existing expert episodes as demonstration and transitions from the interaction between the agent and task environment, which potentially reduce risk from adversarial attack. We propose a variable delay learning mechanism to improve the performance of the proposed algorithm. The simulation results show that our method can converge faster and has a more robust performance with adversarial attack than the existing DRL method under the premise of solving the AUV surfacing control tasks for safety.

Intelligent fault diagnosis of rolling bearings has advanced significantly with the increase in labeled industrial data. However, the limited data for unknown working conditions poses a challenge to the generalization capabilities of current deep learning methods. Therefore, this article proposes a novel approach to domain generalization, leveraging a combination of covariance loss and graph convolutional networks to realize feature augmentation for intelligent fault diagnosis. This method employs random receptive field layers in feature extractors to project inputs from each source domain into distinct feature spaces. Moreover, a covariance loss is incorporated to ensure the dissimilarity of feature representations. Consequently, the augmented features contribute to the construction of an expanded adjacency matrix and prototypes within graph convolutional networks, thereby enhancing the model's capacity to generalize to unknown domains. Results on both a public dataset and an experimental dataset of rolling bearings have shown the superiority of the proposed approach.

Currently, with the development of the Internet of Things (IoTs) and artificial intelligence, a new IoT structure known as the artificial Intelligence of Things (AIoTs) comes into play. With the development of AIoT, a large amount of unlabeled industrial big data has been accumulated. The analysis of large amounts of unlabeled data is labor-intensive and time-consuming for diagnostic personnel. To improve this situation, a novel two-stage unsupervised fault recognition algorithm, namely, deep adaptive fuzzy clustering algorithm (DAFC) is proposed for unsupervised fault clustering in this article. DAFC amalgamates stacked sparse autoencoder (SSAE) into adaptive weighted Gath–Geva (AWGG) clustering to form an unsupervised fault recognition framework for clustering analysis of unlabeled industrial big data. SSAE can extract the highly abstract features of the original data, and adopt different unsupervised strategies to fine-tune the network in two stages. AWGG is an improvement of Gath–Geva clustering, and can adaptively obtain optimal clustering results without presetting the number of clusters. Experimental results on two different datasets show that the proposed DAFC can stably extract fault features from unlabeled data, and automatically obtain the optimal clustering results without knowing the number of clusters in advance. To the best of our knowledge, this article is the first attempt to fine-tune SSAE in an unsupervised manner, and to propose an unsupervised fault recognition framework that requires no prior knowledge or data labels at all. DAFC can be a feasible industrial big data application for collaborative AIoT. Diagnostic personnel analyze the clustering results obtained by DAFC instead of the original unlabeled data, greatly saving time and labor costs.

Massive industrial data collected from the Industrial Internet-of-Things (IIoT) assets improve data-driven methods for prognostics and health management (PHM) systems. As an important role in PHM, remaining useful life (RUL) prediction is essential to maintain the reliability and safety of industrial manufacture. However, recent data-driven approaches for bearing RUL prediction do not weight the contributions of data from different sensors and time steps, which decreases the efficiency in the big data era. In this context, we present a deep learning-based RUL prediction method with an attention mechanism to weight sequence data representations. Specifically, the proposed method weights different industrial sensors and time steps, respectively, based on the distributed attention mechanism. Then, temporal convolution modules with the shared weights are used for feature extraction of time series. Finally, the performance of the proposed method is verified using a popular data set C-MAPSS. The experimental results reveal that the proposed method has high accuracy and is efficient in practical applications.

Nowadays, the industrial Internet of Things (IIoT) has been successfully utilized in smart manufacturing. The massive amount of data in IIoT promote the development of deep learning-based health monitoring for industrial equipment. Since monitoring data for mechanical fault diagnosis collected on different working conditions or equipment have domain mismatch, models trained with training data may not work in practical applications. Therefore, it is essential to study fault diagnosis methods with domain adaptation ability. In this article, we propose an intelligent fault diagnosis method based on an improved domain adaptation method. Specifically, two feature extractors concerning feature space distance and domain mismatch are trained using maximum mean discrepancy and domain adversarial training respectively to enhance feature representation. Since separate classifiers are trained for feature extractors, ensemble learning is further utilized to obtain final results. Experimental results indicate that the proposed method is effective and applicable in diagnosing faults with domain mismatch.

Data-driven fault diagnosis is essential for the reliability and safety of industry equipment. However, the lack of real labeled fault data make the machine learning-based diagnosis methods difficult to carry out. To solve this problem, this article proposes a new fault diagnosis framework called multilabel one-dimensional (1-D) generation adversarial network (ML1-D-GAN). In our method, Auxiliary Classifier GAN is utilized first for real damage data generation. Then the generated and real damage data are both used to train the fault classifier. Experimental results reveal that the generated data is applicable, and ML1-D-GAN improves the diagnosing accuracy for real bearing faults from 95% to 98% when trained with the generated data. The scalability of the learning model is also proven in the experiment.

Industrial Internet of Things (IIoT) obtains big data from industrial facilities. Based on these data, health conditions for facilities can be predicted using machine learning methods, which in turn improves the trustworthiness of IIoT. Intelligent fault diagnosis is developing with this process. Since machine damages always happen under different circumstances, the designed intelligent fault diagnosis methods should have domain adaption ability. In this article, a data-driven fault diagnosis method called domain adaption network (DAN) is present, in which the difference between training and testing data can be minimized while the maximum training accuracy can be maintained. First, DAN uses a combined loss for consistent feature learning and optimum training classification performance. Then, a DAN retraining (DAN-R) strategy is employed based on weighted pseudo-labeled testing dataset. Finally, three experiments are performed on two fault diagnosis datasets. The results reveal that DAN-R is applicable and has outstanding domain adaption ability.

Energy is the most limited resource for sustainable systems, especially battery-based systems, such as Wireless Sensor Network (WSN) or Cyber-Physical System (CPS) nodes. Harvesting energy from a deployed environment is proved to be a feasible method to enable a sustainable operation. Meanwhile, field-programmable gate arrays (FPGAs), which are a reconfigurable fabric, are widely used in sustainable systems. Various applications can be configured into FPGA as required. The available energy varies during the harvesting process. Therefore, configuring FPGA to match the processing requirement within the varied energy is an important issue. As opposed to the traditional scheduling methods that solely focus on reducing computational energy, we adapted a weather forecast method in studying the history data to predict the future harvested data in this study. The predicted future harvested energy was then used in energy-based scheduling. Experiment results indicate that reconfigurable hardware can save up to 50 percent energy compared to software-based execution. Using the weather forecasted scheduling method can execute 35 percent more task compared to the past-predict-future method.

Summary Currently, the rapid increment of human detections has been changing people's daily life, However, the implementation is still facing the challenges caused by the restrictions of power and hardware. The computation process results in a heavy workload even though prior researches had made efforts to reduce the complexity. We focus on this issue and propose a new approach that employs the binarization‐based optimization algorithm to simplify the computation processes. Our approach is designed to minimize the necessary calculations and memory space. Moreover, we have developed the field‐programmable gate array‐based parallel architecture to apply partial dynamic reconfiguration, which enables the remote configurations for the number of processing units. An experimental evaluation is completed in order to examine our proposed approach. According to our experimental results, the detection precision can reach a miss rate less than 1.97% and a false positive rate of 1%. The energy cost is also reduced up to 36% comparing with the prior methods. Copyright © 2016 John Wiley & Sons, Ltd.

In smart city, all kinds of users' data are stored in electronic devices to make everything intelligent. A smartphone is the most widely used electronic device and it is the pivot of all smart systems. However, current smartphones are not competent to manage users' sensitive data, and they are facing the privacy leakage caused by data over-collection. Data over-collection, which means smartphones apps collect users' data more than its original function while within the permission scope, is rapidly becoming one of the most serious potential security hazards in smart city. In this paper, we study the current state of data over-collection and study some most frequent data over-collected cases. We present a mobile-cloud framework, which is an active approach to eradicate the data over-collection. By putting all users' data into a cloud, the security of users' data can be greatly improved. We have done extensive experiments and the experimental results have demonstrated the effectiveness of our approach.

The dramatically growing demand of Cyber Physical and Social Computing (CPSC) has enabled a variety of novel channels to reach services in the financial industry. Combining cloud systems with multimedia big data is a novel approach for Financial Service Institutions (FSIs) to diversify service offerings in an efficient manner. However, the security issue is still a great issue in which the service availability often conflicts with the security constraints when the service media channels are varied. This paper focuses on this problem and proposes a novel approach using the Semantic-Based Access Control (SBAC) techniques for acquiring secure financial services on multimedia big data in cloud computing. The proposed approach is entitled IntercroSsed Secure Big Multimedia Model (2SBM), which is designed to secure accesses between various media through the multiple cloud platforms. The main algorithms supporting the proposed model include the Ontology-Based Access Recognition (OBAR) Algorithm and the Semantic Information Matching (SIM) Algorithm . We implement an experimental evaluation to prove the correctness and adoptability of our proposed scheme.

Hardware implementation of human detection is a challenging task for embedded designs. This paper presents a real-time image-based field-programmable gate array (FPGA) implementation of human detection. Our implementation is based on the histograms of oriented gradients (HOG) feature and linear support vector machine (SVM) classifier. The novelty of this work is that we replace normalization process of HOG with a modified binarization process. Therefore, during classification process with SVM classifier, all multiplication operations are replaced by addition operations. All these modifications result in reduction of hardware resource. Experimental evaluation reveals that 293 fps can be achieved on a low-end Xilinx Spartan-3e FPGA. Moreover, a detection accuracy of 1.97% miss rate and 1% false positive rate is achieved. For further demonstration, a prototype system is developed with an OV7670 camera device. Restricted to the speed of camera, a detection rate of 30 fps is achieved.