In this research, the authors demonstrate the advantage of reinforcement learning (RL) based intrusion detection systems (IDS) to solve very complex problems (e.g. selecting input…
Abstract
Purpose
In this research, the authors demonstrate the advantage of reinforcement learning (RL) based intrusion detection systems (IDS) to solve very complex problems (e.g. selecting input features, considering scarce resources and constrains) that cannot be solved by classical machine learning. The authors include a comparative study to build intrusion detection based on statistical machine learning and representational learning, using knowledge discovery in databases (KDD) Cup99 and Installation Support Center of Expertise (ISCX) 2012.
Design/methodology/approach
The methodology applies a data analytics approach, consisting of data exploration and machine learning model training and evaluation. To build a network-based intrusion detection system, the authors apply dueling double deep Q-networks architecture enabled with costly features, k-nearest neighbors (K-NN), support-vector machines (SVM) and convolution neural networks (CNN).
Findings
Machine learning-based intrusion detection are trained on historical datasets which lead to model drift and lack of generalization whereas RL is trained with data collected through interactions. RL is bound to learn from its interactions with a stochastic environment in the absence of a training dataset whereas supervised learning simply learns from collected data and require less computational resources.
Research limitations/implications
All machine learning models have achieved high accuracy values and performance. One potential reason is that both datasets are simulated, and not realistic. It was not clear whether a validation was ever performed to show that data were collected from real network traffics.
Practical implications
The study provides guidelines to implement IDS with classical supervised learning, deep learning and RL.
Originality/value
The research applied the dueling double deep Q-networks architecture enabled with costly features to build network-based intrusion detection from network traffics. This research presents a comparative study of reinforcement-based instruction detection with counterparts built with statistical and representational machine learning.
Details
Keywords
Giuliana Isabella and Valter Afonso Vieira
The purpose of this paper is to investigate the emotional contagion theory in print ads, and expand the literature of smiling to different type of smiles and gender congruency…
Abstract
Purpose
The purpose of this paper is to investigate the emotional contagion theory in print ads, and expand the literature of smiling to different type of smiles and gender congruency. Emotional contagion happens when an emotion is transferred from a sender to a receiver by the synchronization of emotions from the emitter. Drawing on emotional contagion theory, the authors expand this concept and propose that smiles in static facial expressions influence product evaluation. They suggest that false smiles do not have the same impact as genuine smiles on product evaluation, and the congruence between the model gender–product in a static ad and the gender of the viewer moderates the effects.
Design/methodology/approach
In Experiment 1, subjects were randomly assigned to view one of the two ad treatments to guard against systematic error (e.g. bias). In Experiment 2, it was investigated whether viewing a static ad featuring a model with a false smile can result in a positive product evaluation as was the case with genuine smiles (H3). In Experiment 3, it was assumed that when consumers evaluate an ad featuring a smiling face, the facial expression influences product evaluation, and this influence is moderated by the congruence between the gender of the ad viewer and the product H gender of the model in the ad.
Findings
Across three experiments, the authors found that the model’s facial expression influenced the product evaluation. Second, they supported the association between a model’s facial expression and mimicry synchronization. Third, they showed that genuine smiles have a higher impact on product evaluation than false smiles. This novel result enlarges the research on genuine smiles to include false smiles. Fourth, the authors supported the gender–product congruence effect in that the gender of the ad’s reader and the model have a moderating effect on the relationship between the model’s facial expression and the reader’s product evaluation.
Originality/value
Marketing managers would benefit from understanding that genuine smiles can encourage positive emotions on the part of consumers via emotional contagion, which would be very useful to create a positive effect on products. The authors improved upon previous psychological theory (Gunnery et al., 2013; Hennig-Thurau et al., 2006) showing that a genuine smile results in higher evaluation scores of products presented in static ads. The theoretical explanation for this effect is the genuine smile, which involves contraction of both zygomatic major and orbicularis oculi muscles. These facial muscles can be better perceived and transmit positive emotions (Hennig-Thurau et al., 2006).
Details
Keywords
Ning Qian, Muhammad Jamil, Wenfeng Ding, Yucan Fu and Jiuhua Xu
This paper is supposed to provide a critical review of current research progress on thermal management in grinding of superalloys, and future directions and challenges. By…
Abstract
Purpose
This paper is supposed to provide a critical review of current research progress on thermal management in grinding of superalloys, and future directions and challenges. By understanding the current progress and identifying the developing directions, thermal management can be achieved in the grinding of superalloys to significantly improve the grinding quality and efficiency.
Design/methodology/approach
The relevant literature is collected from Web of Science, Scopus, CNKI, Google scholar, etc. A total of 185 literature is analyzed, and the findings in the literature are systematically summarized. In this case, the current development and future trends of thermal management in grinding of superalloys can be concluded.
Findings
The recent developments in grinding superalloys, demands, challenges and solutions are analyzed. The theoretical basis of thermal management in grinding, the grinding heat partition analysis, is also summarized. The novel methods and technologies for thermal management are developed and reviewed, i.e. new grinding technologies and parameter optimization, super abrasive grinding wheel technologies, improved lubrication, highly efficient coolant delivery and enhanced heat transfer by passive thermal devices. Finally, the future trends and challenges are identified.
Originality/value
Superalloys have excellent physical and mechanical properties, e.g. high thermal stability, and good high-temperature strength. The superalloys have been broadly applied in the aerospace, energy and automobile industries. Grinding is one of the most important precision machining technologies for superalloy parts. Owing to the mechanical and physical properties of superalloys, during grinding processes, forces are large and a massive heat is generated. Consequently, the improvement of grinding quality and efficiency is limited. It is important to conduct thermal management in the grinding of superalloys to decrease grinding forces and heat generation. The grinding heat is also dissipated in time by enhanced heat transfer methods. Therefore, it is necessary and valuable to holistically review the current situation of thermal management in grinding of superalloys and also provide the development trends and challenges.
Details
Keywords
Qingqing Wu, Xianguan Zhao, Lihua Zhou, Yao Wang and Yudi Yang
With the rapid development of internet technology, open online social networks provide a broader platform for information spreading. While dissemination of information provides…
Abstract
Purpose
With the rapid development of internet technology, open online social networks provide a broader platform for information spreading. While dissemination of information provides convenience for life, it also brings many problems such as security risks and public opinion orientation. Various negative, malicious and false information spread across regions, which seriously affect social harmony and national security. Therefore, this paper aims to minimize negative information such as online rumors that has attracted extensive attention. The most existing algorithms for blocking rumors have prevented the spread of rumors to some extent, but these algorithms are designed based on entire social networks, mainly focusing on the microstructure of the network, i.e. the pairwise relationship or similarity between nodes. The blocking effect of these algorithms may be unsatisfactory in some networks because of the sparse data in the microstructure.
Design/methodology/approach
An algorithm for minimizing the influence of dynamic rumor based on community structure is proposed in this paper. The algorithm first divides the network into communities, and integrates the influence of each node within communities and rumor influence probability to measure the influence of each node in the entire network, and then selects key nodes and bridge nodes in communities as blocked nodes. After that, a dynamic blocking strategy is adopted to improve the blocking effect of rumors.
Findings
Community structure is one of the most prominent features of networks. It reveals the organizational structure and functional components of a network from a mesoscopic level. The utilization of community structure can provide effective and rich information to solve the problem of data sparsity in the microstructure, thus effectively improve the blocking effect. Extensive experiments on two real-world data sets have validated that the proposed algorithm has superior performance than the baseline algorithms.
Originality/value
As an important research direction of social network analysis, rumor minimization has a profound effect on the harmony and stability of society and the development of social media. However, because the rumor spread has the characteristics of multiple propagation paths, fast propagation speed, wide propagation area and time-varying, it is a huge challenge to improve the effectiveness of the rumor blocking algorithm.
Details
Keywords
Yixin Zhang, Lizhen Cui, Wei He, Xudong Lu and Shipeng Wang
The behavioral decision-making of digital-self is one of the important research contents of the network of crowd intelligence. The factors and mechanisms that affect…
Abstract
Purpose
The behavioral decision-making of digital-self is one of the important research contents of the network of crowd intelligence. The factors and mechanisms that affect decision-making have attracted the attention of many researchers. Among the factors that influence decision-making, the mind of digital-self plays an important role. Exploring the influence mechanism of digital-selfs’ mind on decision-making is helpful to understand the behaviors of the crowd intelligence network and improve the transaction efficiency in the network of CrowdIntell.
Design/methodology/approach
In this paper, the authors use behavioral pattern perception layer, multi-aspect perception layer and memory network enhancement layer to adaptively explore the mind of a digital-self and generate the mental representation of a digital-self from three aspects including external behavior, multi-aspect factors of the mind and memory units. The authors use the mental representations to assist behavioral decision-making.
Findings
The evaluation in real-world open data sets shows that the proposed method can model the mind and verify the influence of the mind on the behavioral decisions, and its performance is better than the universal baseline methods for modeling user interest.
Originality/value
In general, the authors use the behaviors of the digital-self to mine and explore its mind, which is used to assist the digital-self to make decisions and promote the transaction in the network of CrowdIntell. This work is one of the early attempts, which uses neural networks to model the mental representation of digital-self.
Details
Keywords
Haiyan Jiang, Jing Jia and Yuanyuan Hu
This study aims to investigate whether firms purchase directors' and officers' liability (D&O) insurance when the country-level economic policy uncertainty (EPU) is high.
Abstract
Purpose
This study aims to investigate whether firms purchase directors' and officers' liability (D&O) insurance when the country-level economic policy uncertainty (EPU) is high.
Design/methodology/approach
This study uses D&O insurance data from Chinese listed firms between 2003 and 2019 to conduct regression analyses to examine the association between D&O insurance and EPU.
Findings
The results show that government EPU, despite being an exogenous factor, increases the likelihood of firms' purchasing D&O insurance, and this effect is more pronounced when firms are exposed to great share price crash risk and high litigation risk, suggesting that firms intend to purchase D&O insurance possibly due to the accentuated stock price crash risk and litigation risk associated with EPU. In addition, the results indicate that the effect of EPU on the D&O insurance purchase decision is moderated by the provincial capital market development and internal control quality.
Practical implications
The study highlights the role of uncertain economic policies in shareholder approval of D&O insurance purchases.
Originality/value
The study enriches the literature on the determinants of D&O insurance purchases by documenting novel evidence that country-level EPU is a key institutional factor shaping firms' decisions to purchase D&O insurance.
Details
Keywords
Xudong Lu, Shipeng Wang, Fengjian Kang, Shijun Liu, Hui Li, Xiangzhen Xu and Lizhen Cui
The purpose of this paper is to detect abnormal data of complex and sophisticated industrial equipment with sensors quickly and accurately. Due to the rapid development of the…
Abstract
Purpose
The purpose of this paper is to detect abnormal data of complex and sophisticated industrial equipment with sensors quickly and accurately. Due to the rapid development of the Internet of Things, more and more equipment is equipped with sensors, especially more complex and sophisticated industrial equipment is installed with a large number of sensors. A large amount of monitoring data is quickly collected to monitor the operation of the equipment. How to detect abnormal data quickly and accurately has become a challenge.
Design/methodology/approach
In this paper, the authors propose an approach called Multiple Group Correlation-based Anomaly Detection (MGCAD), which can detect equipment anomaly quickly and accurately. The single-point anomaly degree of equipment and the correlation of each kind of data sequence are modeled by using multi-group correlation probability model (a probability distribution model which is helpful to the anomaly detection of equipment), and the anomaly detection of equipment is realized.
Findings
The simulation data set experiments based on real data show that MGCAD has better performance than existing methods in processing multiple monitoring data sequences.
Originality/value
The MGCAD method can detect abnormal data quickly and accurately, promote the intelligent level of smart articles and ultimately help to project the real world into cyber space in CrowdIntell Network.
Details
Keywords
Ming Gao, Dongkai Li, Kun Liu, Shuliang Xu, Feng Zhao, Ben Guo, Anhui Pan, Xiao Xie and Huanre Han
The brake pipe system was an essential braking component of the railway freight trains, but the existing E-type sealing rings had problems such as insufficient low-temperature…
Abstract
Purpose
The brake pipe system was an essential braking component of the railway freight trains, but the existing E-type sealing rings had problems such as insufficient low-temperature resistance, poor heat stability and short service life. To address these issues, low-phenyl silicone rubber was prepared and tested, and the finite element analysis and experimental studies on the sealing performance of its sealing rings were carried out.
Design/methodology/approach
The low-temperature resistance and thermal stability of the prepared low-phenyl silicone rubber were studied using low-temperature tensile testing, differential scanning calorimetry, dynamic thermomechanical analysis and thermogravimetric analysis. The sealing performance of the low-phenyl silicone rubber sealing ring was studied by using finite element analysis software abaqus and experiments.
Findings
The prepared low-phenyl silicone rubber sealing ring possessed excellent low-temperature resistance and thermal stability. According to the finite element analysis results, the finish of the flange sealing surface and groove outer edge should be ensured, and extrusion damage should be avoided. The sealing rings were more susceptible to damage in high compression ratio and/or low-temperature environments. When the sealing effect was ensured, a small compression ratio should be selected, and rubbers with hardness and elasticity less affected by temperature should be selected. The prepared low-phenyl silicone rubber sealing ring had zero leakage at both room temperature (RT) and −50 °C.
Originality/value
The innovation of this study is that it provides valuable data and experience for the future development of the sealing rings used in the brake pipe flange joints of the railway freight cars in China.
Details
Keywords
Adela Socol and Iulia Cristina Iuga
This study aims to investigate the impact of brain drain on government AI readiness in EU member countries, considering the distinctive governance characteristics, macroeconomic…
Abstract
Purpose
This study aims to investigate the impact of brain drain on government AI readiness in EU member countries, considering the distinctive governance characteristics, macroeconomic conditions and varying levels of ICT specialists.
Design/methodology/approach
The research employs a dynamic panel data model using the System Generalized Method of Moments (GMM) to analyze the relationship between brain drain and government AI readiness from 2018 to 2022. The study incorporates various control variables such as GDP per capita growth, government expenditure growth, employed ICT specialists and several governance indicators.
Findings
The results indicate that brain drain negatively affects government AI readiness. Additionally, the presence of ICT specialists, robust governance structures and positive macroeconomic indicators such as GDP per capita growth and government expenditure growth positively influence AI readiness.
Research limitations/implications
Major limitations include the focus on a specific region of countries and the relatively short period analyzed. Future research could extend the analysis with more comprehensive datasets and consider additional variables that might influence AI readiness, such as the integration of AI with emerging quantum computing technologies and the impact of governance reforms and international collaborations on AI readiness.
Practical implications
The theoretical value of this study lies in providing a nuanced understanding of how brain drain impacts government AI readiness, emphasizing the critical roles of skilled human capital, effective governance and macroeconomic factors in enhancing AI capabilities, thereby filling a significant gap in the existing literature.
Originality/value
This research fills a significant gap in the existing literature by providing a comprehensive analysis of the interaction between brain drain and government AI readiness. It uses control variables such as ICT specialists, governance structures and macroeconomic factors within the context of the European Union. It offers novel insights for policymakers to enhance AI readiness through targeted interventions addressing brain drain and fostering a supportive environment for AI innovation.
Details
Keywords
Hongping Xing, Yu Liu and Xiaodan Sun
The smoothness of the high-speed railway (HSR) on the bridge may exceed the allowable standard when an earthquake causes vibrations for HSR bridges, which may threaten the safety…
Abstract
Purpose
The smoothness of the high-speed railway (HSR) on the bridge may exceed the allowable standard when an earthquake causes vibrations for HSR bridges, which may threaten the safety of running trains. Indeed, few studies have evaluated the exceeding probability of rail displacement exceeding the allowable standard. The purposes of this article are to provide a method for investigating the exceeding probability of the rail displacement of HSRs under seismic excitation and to calculate the exceeding probability.
Design/methodology/approach
In order to investigate the exceeding probability of the rail displacement under different seismic excitations, the workflow of analyzing the smoothness of the rail based on incremental dynamic analysis (IDA) is proposed, and the intensity measure and limit state for the exceeding probability analysis of HSRs are defined. Then a finite element model (FEM) of an assumed HSR track-bridge system is constructed, which comprises a five-span simply-supported girder bridge supporting a finite length CRTS II ballastless track. Under different seismic excitations, the seismic displacement response of the rail is calculated; the character of the rail displacement is analyzed; and the exceeding probability of the rail vertical displacement exceeding the allowable standard (2mm) is investigated.
Findings
The results show that: (1) The bridge-abutment joint position may form a step-like under seismic excitation, threatening the running safety of high-speed trains under seismic excitations, and the rail displacements at mid-span positions are bigger than that at other positions on the bridge. (2) The exceeding probability of rail displacement is up to about 44% when PGA = 0.01g, which is the level-five risk probability and can be described as 'very likely to happen'. (3) The exceeding probability of the rail at the mid-span positions is bigger than that above other positions of the bridge, and the mid-span positions of the track-bridge system above the bridge may be the most hazardous area for the running safety of trains under seismic excitation when high-speed trains run on bridges.
Originality/value
The work extends the seismic hazardous analysis of HSRs and would lead to a better understanding of the exceeding probability for the rail of HSRs under seismic excitations and better references for the alert of the HSR operation.