Showing papers by "Beijing University of Posts and Telecommunications published in 2022"

Trustworthy Target Tracking With Collaborative Deep Reinforcement Learning in EdgeAI-Aided IoT

Abstract: Mobile target tracking with artificial intelligence (AI) approaches such as deep reinforcement learning (DRL) in edge-assisted Internet of Things (Edge-IoT) platform can be promising. In this article, we propose DRLTrack , a framework for target tracking with a collaborative DRL called C-DRL in Edge-IoT with the aim to obtain two major objectives: high quality of tracking (QoT) and resource-efficient network performance. In DRLTrack , a huge number of IoT devices are employed to collect data about a target of interest. One or two edge devices in the network coordinate with a group of IoT devices and collaboratively detect the target by using the C-DRL approach and form an area around the target by the group of IoT devices. To maintain such an area during the tracking time, we employ a deep Q-network to track the target from one group to another. An EdgeAI sitting on the top of the edge devices has the control of the C-DRL approach during tracking and can identify a sequence of tracks. DRLTrack is said to be trustworthy as it shows trustworthy performance in terms of QoT, dynamic environments, and even under certain cyberattacks. We validate the performance of DRLTrack considering the objectives through simulations and it demonstrates superior performance compared with existing work.

IoT data visualization for business intelligence in corporate finance

Abstract: Business intelligence (BI) incorporates business research, data mining, data visualization, data tools,infrastructure, and best practices to help businesses make more data-driven choices.Business intelligence's challenging characteristics include data breaches, difficulty in analyzing different data sources, and poor data quality is consideredessential factors. In this paper, IoT-based Efficient Data Visualization Framework (IoT- EDVF) has been proposed to strengthen leaks' risk, analyze multiple data sources, and data quality management for business intelligence in corporate finance.Corporate analytics management is introduced to enhance the data analysis system's risk, and the complexity of different sources can allow accessing Business Intelligence. Financial risk analysis is implemented to improve data quality management initiative helps use main metrics of success, which are essential to the individual needs and objectives. The statistical outcomes of the simulation analysis show the increasedperformance with a lower delay response of 5ms and improved revenue analysis with the improvement of 29.42% over existing models proving the proposed framework's reliability.

Efficient privacy-preserving user authentication scheme with forward secrecy for industry 4.0

Abstract: Industry 4.0, which combines information technology, network and industrial production, is expected to have a tremendous impact on our daily lives. In such a complex and security-critical system with resource-constrained sensor nodes, the design of a secure user authentication scheme for preventing real-time data from unauthorized access is full of challenges, and the main crux lies in how to realize the important property of forward secrecy. Existing schemes either fail to achieve forward secrecy or achieve forward secrecy with high computation cost on sensor nodes. Besides, they often fail to conform to the development trend of industry 4.0 systems where a cloud center is necessary to help intelligent decision-making and alleviate computation and storage pressure. Therefore, in this paper, we propose an efficient privacy-preserving user authentication scheme with forward secrecy for industry 4.0, and formally prove its security in the random oracle model. Compared with previous schemes, it has three advantages: (1) all eleven state-of-the-art criteria are achieved; (2) its computation cost on sensor nodes is comparable to those insecure schemes that employ only symmetric cryptographic algorithms, and is superior to those that also use asymmetric cryptographic algorithms; (3) it takes the advantage of the computation and storage capabilities of the cloud center to achieve user anonymity and the resistance to offline dictionary attack without performing any asymmetric cryptographic algorithms on gateways. Our computation cost on gateways is the smallest among all state-of-the-art relevant schemes for comparison.

Modified Remora Optimization Algorithm for Global Optimization and Multilevel Thresholding Image Segmentation

Abstract: Image segmentation is a key stage in image processing because it simplifies the representation of the image and facilitates subsequent analysis. The multi-level thresholding image segmentation technique is considered one of the most popular methods because it is efficient and straightforward. Many relative works use meta-heuristic algorithms (MAs) to determine threshold values, but they have issues such as poor convergence accuracy and stagnation into local optimal solutions. Therefore, to alleviate these shortcomings, in this paper, we present a modified remora optimization algorithm (MROA) for global optimization and image segmentation tasks. We used Brownian motion to promote the exploration ability of ROA and provide a greater opportunity to find the optimal solution. Second, lens opposition-based learning is introduced to enhance the ability of search agents to jump out of the local optimal solution. To substantiate the performance of MROA, we first used 23 benchmark functions to evaluate the performance. We compared it with seven well-known algorithms regarding optimization accuracy, convergence speed, and significant difference. Subsequently, we tested the segmentation quality of MORA on eight grayscale images with cross-entropy as the objective function. The experimental metrics include peak signal-to-noise ratio (PSNR), structure similarity (SSIM), and feature similarity (FSIM). A series of experimental results have proved that the MROA has significant advantages among the compared algorithms. Consequently, the proposed MROA is a promising method for global optimization problems and image segmentation.

Intelligent-Driven Green Resource Allocation for Industrial Internet of Things in 5G Heterogeneous Networks

Abstract: The Industrial Internet of Things (IIoT) is one of the important applications under the 5G massive machine type of communication (mMTC) scenario. To ensure the high reliability of IIoT services, it is necessary to apply an efficient resource allocation method under the dynamic and complex environment. In view of the absence of energy-efficient resource management architecture for the entire network, this article proposes an intelligent-driven green resource allocation mechanism for the IIoT under 5G heterogeneous networks. First, an intelligent end-to-end self-organizing resource allocation framework for IIoT service is given. Next, an energy-efficient resource allocation model within the framework is proposed. It is then solved by an intelligent mechanism with the asynchronous advantage actor critic driven deep reinforcement learning algorithm. Through the comparison analysis of different methods and rewards under IIoT scenarios with proper parameters setting, the proposed method can achieve better performance than other traditional deep learning (DL) methods and maintain service quality above accepted levels as well.

Electrophotocatalytic C−H Functionalization of N‐Heteroarenes with Unactivated Alkanes under External Oxidant‐Free Conditions

Abstract: The Minisci alkylation of N-heteroarenes with unactivated alkanes under external oxidant-free conditions provides an economically attractive route to access alkylated N-heteroarenes but remains underdeveloped. Herein, a new electrophotocatalytic strategy to access alkyl radicals from strong C(sp3 )-H bonds was reported for the following Minisci alkylation reactions in the absence of chemical oxidants. This strategy realized the first example of cerium-catalyzed Minisci alkylation reaction directly from abundant unactivated alkanes with excellent atom economy. It is anticipated that the general design principle would enrich catalytic strategies to explore the functionalizations of strong C(sp3 )-H bonds under external oxidant-free conditions with H2 evolution.

Calcium-magnesium-alumina-silicate (CMAS) resistant high entropy ceramic (Y0.2Gd0.2Er0.2Yb0.2Lu0.2)2Zr2O7 for thermal barrier coatings

Abstract: A novel high-entropy material, (Y0.2Gd0.2Er0.2Yb0.2Lu0.2)2Zr2O7 was successfully synthesized by the solid state reaction method and spark plasma sintering, and investigated as a promising thermal barrier coating material. Rare-earth elements were distributed homogeneously in the pyrochlore structure. It was found that the prepared high-entropy ceramic maintains pyrochlore structure at the temperature up to 1600 °C, and it possesses a similar thermal expansion coefficient (10.2 × 10−6 K−1 at 25–900 °C) to that of YSZ, low thermal conductivity (< 0.9 W m−1 K−1 at 100–1000 °C) and good CMAS resistance (infiltration depth is 22 μm after annealed at 1300 °C for 24 h). The corrosion process was investigated, and RE elements distributing homogeneously in (Y0.2Gd0.2Er0.2Yb0.2Lu0.2)2Zr2O7 show different diffusion rates in CMAS. RE3+ with a larger radius (closer to Ca2+) is easier to react with CMAS to form an apatite phase.

Direct Z-scheme polymeric heterojunction boosts photocatalytic hydrogen production <i>via</i> a rebuilt extended π-delocalized network

Abstract: We propose a strategy to rebuild the extended π-delocalized network in a Z-scheme polymeric heterojunction to improve the photon utilization efficiency, engendering an unprecedentedly high photocatalytic performance.

Clinical Eosinophil-Associated Genes can Serve as a Reliable Predictor of Bladder Urothelial Cancer

Abstract: Background: Numerous studies have shown that infiltrating eosinophils play a key role in the tumor progression of bladder urothelial carcinoma (BLCA). However, the roles of eosinophils and associated hub genes in clinical outcomes and immunotherapy are not well known. Methods: BLCA patient data were extracted from the TCGA database. The tumor immune microenvironment (TIME) was revealed by the CIBERSORT algorithm. Candidate modules and hub genes associated with eosinophils were identified by weighted gene co-expression network analysis (WGCNA). The external GEO database was applied to validate the above results. TIME-related genes with prognostic significance were screened by univariate Cox regression analysis, lasso regression, and multivariate Cox regression analysis. The patient's risk score (RS) was calculated and divided subjects into high-risk group (HRG) and low-risk group (LRG). The nomogram was developed based on the risk signature. Models were validated via receiver operating characteristic (ROC) curves and calibration curves. Differences between HRG and LRG in clinical features and tumor mutational burden (TMB) were compared. The Immune Phenomenon Score (IPS) was calculated to estimate the immunotherapeutic significance of RS. Half-maximal inhibitory concentrations (IC50s) of chemotherapeutic drugs were predicted by the pRRophetic algorithm. Results: 313 eosinophil-related genes were identified by WGCNA. Subsequently, a risk signature containing 9 eosinophil-related genes (AGXT, B3GALT2, CCDC62, CLEC1B, CLEC2D, CYP19A1, DNM3, SLC5A9, SLC26A8) was finally developed via multiplex analysis and screening. Age (p < 0.001), grade (p < 0.001), and RS (p < 0.001) were independent predictors of survival in BLCA patients. Based on the calibration curve, our risk signature nomogram was confirmed as a good predictor of BLCA patients' prognosis at 1, 3, and 5 years. The association analysis of RS and immunotherapy indicated that low-risk patients were more credible for novel immune checkpoint inhibitors (ICI) immunotherapy. The chemotherapeutic drug model suggests that RS has an effect on the drug sensitivity of patients. Conclusions: In conclusion, the eosinophil-based RS can be used as a reliable clinical predictor and provide insights into the precise treatment of BLCA.