Residual attention-based tracking-by-detection network with attention-driven data augmentation

Tracking-by-detection (TBD) is a significant framework for visual object tracking. However, current trackers are usually updated online based on random sampling with a probability distribution. The performance of the learning-based TBD trackers is limited by the lack of discriminative features, especially when the background is full of semantic distractors. We propose an attention-driven data augmentation method, in which a residual attention mechanism is integrated into the TBD tracking network as supplementary references to identify discriminative image features. A mask generating network is used to simulate changes in target appearances to obtain positive samples, where attention information and image features are combined to identify discriminative features. In addition, we propose a method for mining hard negative samples, which searches for semantic distractors with the response of the attention module. The experiments on the OTB2015, UAV123, and LaSOT benchmarks show that this method achieves competitive performance in terms of accuracy and robustness.     

Data fusion and transfer learning empowered granular trust evaluation for Internet of Things

In the Internet of Things (IoT), a huge amount of valuable data is generated by various IoT applications. As the IoT technologies become more complex, the attack methods are more diversified and can cause serious damages. Thus, establishing a secure IoT network based on user trust evaluation to defend against security threats and ensure the reliability of data source of collected data have become urgent issues, in this paper, a Data Fusion and transfer learning empowered granular Trust Evaluation mechanism (DFTE) is proposed to address the above challenges. Specifically, to meet the granularity demands of trust evaluation, time–space empowered fine/coarse grained trust evaluation models are built utilizing deep transfer learning algorithms based on data fusion. Moreover, to prevent privacy leakage and task sabotage, a dynamic reward and punishment mechanism is developed to encourage honest users by dynamically adjusting the scale of reward or punishment and accurately evaluating users’ trusts. The extensive experiments show that: (i) the proposed DFTE achieves high accuracy of trust evaluation under different granular demands through efficient data fusion; (ii) DFTE performs excellently in participation rate and data reliability.     

安卓平台上的医用图像信息采集系统的开发设计

为了探讨在安卓平台上构建医用图像采集系统的开发个案,分析通过以智能手机、平板电脑为核心安卓设备通过拍照获得化验单数据后进行文本识别并提交智慧医疗系统的解决方案。本文首先通过二值化算法形成低阈值图像数据,使用卷积神经元网络算法对文本进行逐一识别,使用K-means算法对识别后的单字文本进行字段记录值的整合并形成元数据库服务于其他智慧医疗系统模块。在使用9000组数据对神经元网络进行前期训练的前提下,该系统的识别准确率达到了99.5%以上。本系统具有一定的可行性,对未来智慧医疗的系统开发有实践意义。     

Main trends on the simulation of the drying of refractory castables - Review

Refractory castables develop microstructures after curing that behave as partially saturated porous media. Upon heating (during its drying stage), the steam generated by the physical and chemically bond water can result in pore pressurization and explosive spalling. Numerical modeling can provide guidelines for designing safer heat-up profiles and also a better understanding of the mechanisms that lead to catastrophic damage. This work aims to review the fundamentals and models available, providing insightful thoughts on the current trends of the drying phenomena of ceramic compositions. The review also highlights that there are models better oriented to result in reasonable predictions of pore pressure values and others focused on a more accurate representation of the main physical phenomena that take place during heating. According to the findings, there are still various challenges to attain accurate models with high applicability capable of yielding safer and more efficient drying of refractory castables.     

Development of autonomous monitoring and performance evaluation system of grid-tied photovoltaic station

This work aims to improve the existing monitoring systems MS for two grid-connected PV stations GCPVS of URERMS ADRAR, to eliminate its limitations. This improvement consists of developing an MS which is used for two PV stations with different configurations. This MS contains new LabVIEW-based monitoring software for visualizing real-time measured data and evaluating GCPVS performance. In addition, it illustrates the 2D and 3D real-time relationships of PV system parameters, which allow us to understand the dynamic behavior of PV system components. This developed monitoring software synchronizes also the various data acquisition units DAU of GCPVS, allowing simultaneous data access.To perform a reliable performance analysis and a comparative study of different GCPVS based on accurate measurements, the sensor's calibration is performed with its DAU. The MS autonomy is ensured by integrating developed PV-UPS. A graphical user interface is provided for the evaluation of PV-UPS performance.     

Prediction of risk factors of cyberbullying-related words in Korea: Application of data mining using social big data

The study examined a decision tree analysis using social big data to conduct the prediction model on types of risk factors related to cyberbullying in Korea. The study conducted an analysis of 103,212 buzzes that had noted causes of cyberbullying and data were collected from 227 online channels, such as news websites, blogs, online groups, social network services, and online bulletin boards. Using opinion-mining method and decision tree analysis, the types of cyberbullying were sorted using SPSS 25.0. The results indicated that the total rate of types of cyberbullying in Korea was 44%, which consisted of 32.3% victims, 6.4% perpetrators, and 5.3% bystanders. According to the results, the impulse factor was also the greatest influence on the prediction of the risk factors and the propensity for dominance factor was the second greatest factor predicting the types of risk factors. In particular, the impulse factor had the most significant effect on bystanders, and the propensity for dominance factor was also significant in influencing online perpetrators. It is necessary to develop a program to diminish the impulses that were initiated by bystanders as well as victims and perpetrators because many of those bystanders have tended to aggravate impulsive cyberbullying behaviors.     

近五年地质学领域研究热点的数据可视化分析

本文选取2016年1月至2021年7月在地质学领域权威期刊：《地质学报》、《岩石学报》、《地学前缘》上发表的文献为研究对象,利用Endnote、Excel和Vosviewer等软件对数据进行相应的整理和清洗,分析了相关热点与关键词的耦合关系。结果显示：在成矿时代同位素定年的研究中,Lu-Hf年代学逐渐成为地学研究的一个热点；随着测试分析手段的进步,西藏地区作为研究青藏高原前寒武纪-早古生代演化历史的关键,逐渐成为当下国内外研究热点地区；随着信息技术的发展,地学研究的数据化、信息化,已成为地质学研究的热门方向。     

A Tradeoff Between Accuracy and Speed for K-Means Seed Determination

With a sharp increase in the information volume, analyzing and retrieving this vast data volume is much more essential than ever. One of the main techniques that would be beneficial in this regard is called the Clustering method. Clustering aims to classify objects so that all objects within a cluster have similar features while other objects in different clusters are as distinct as possible. One of the most widely used clustering algorithms with the well and approved performance in different applications is the k-means algorithm. The main problem of the k-means algorithm is its performance which can be directly affected by the selection in the primary clusters. Lack of attention to this crucial issue has consequences such as creating empty clusters and decreasing the convergence time. Besides, the selection of appropriate initial seeds can reduce the cluster’s inconsistency. In this paper, we present a new method to determine the initial seeds of the k-mean algorithm to improve the accuracy and decrease the number of iterations of the algorithm. For this purpose, a new method is proposed considering the average distance between objects to determine the initial seeds. Our method attempts to provide a proper tradeoff between the accuracy and speed of the clustering algorithm. The experimental results showed that our proposed approach outperforms the Chithra with 1.7% and 2.1% in terms of clustering accuracy for Wine and Abalone detection data, respectively. Furthermore, achieved results indicate that comparing with the Reverse Nearest Neighbor (RNN) search approach, the proposed method has a higher convergence speed.     

A design method of data analytics process for condition based maintenance

Many condition monitoring systems use data analytics processes such as anomaly detection to understand machine conditions. Such data analytics processes have been designed by data scientists. However, domain knowledge is indispensable for designing the process, and data scientists have difficulty in acquiring such knowledge from domain engineers. This paper proposes a design method of data analytics processes and an engineering tool. In this method, data scientists propose hypotheses about each step of the process to domain engineers. Then, data scientists update the process on the basis of feedback from domain engineers. The engineering tool helps data scientists to interact with domain engineers.     

Profiling of knowledge organisation systems for the annotation of Linked Data cultural resources

The importance of cultural heritage for supporting the knowledge economy has promoted its digitisation and online publication. Many cultural heritage repositories have published millions of digitised items using semantic web technologies and Linked Data approaches. These repositories frequently use knowledge organisation systems to classify the resources, but the domain heterogeneity makes it difficult to know if they are the most suitable ones. This paper describes the process used to discover and profile the knowledge organisation systems used in the cultural heritage domain. Additionally, for those knowledge organisation systems with a thesaurus-like structure, a detailed quality analysis is performed. The results of this analysis can be used as a key factor for the selection of knowledge organisation systems in classification tasks.