Template-Type: ReDIF-Article 1.0 Author-Name: Andrei N. Munteanu Author-X-Name-First: Andrei N. Author-X-Name-Last: Munteanu Author-Name: Zorina C. Siscan Author-X-Name-First: Zorina C. Author-X-Name-Last: Siscan Title: Building added value by synergising the economics of education and international economic integration for low-income countries Abstract: Contemporaneous sciences keep searching for new ways out of the crisis, whereas an outstanding, significant scientific event in the most recent history has not been valorised at its full potential. Improper attention paid to economic education in recent decades has caused an ambiguous understanding of the global economic disequilibrium, now being the key trigger of potential larger-scale war(s), when the global community already avails examples of viable, refined peacebuilding. In the 1950s outstanding economic growth started, owing to an unprecedented synergy of: 1) economics of education emerged; 2) international economic integration (IEI). Despite that, an excessive conflict persists, originating in how people perceive economic disequilibria; it is typically attributed to either globalisation or IEI. The role of the R&D is expected as ever, to supply more creative, genuine inputs for a solution. The article aims to supply better tools of comparative policy making in education, to better perform adjustment of LICs to international economic disequilibrium, by synergising Economics of Education and IEI. The added value of this article is to supply premises for potentially enhanced use of the correlation between the EE and IEI, and more acknowledged and motivational diffusion of scientific evidence. Journal: Int. J. of Networking and Virtual Organisations Pages: 125-143 Issue: 2 Volume: 29 Year: 2023 Keywords: economics of education; international economic integration; IEI; synergetics; low-income countries; LICs; comparative content analysis; networking economics. File-URL: http://www.inderscience.com/link.php?id=134983 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:2:p:125-143 Template-Type: ReDIF-Article 1.0 Author-Name: Biao Ma Author-X-Name-First: Biao Author-X-Name-Last: Ma Author-Name: Li Li Author-X-Name-First: Li Author-X-Name-Last: Li Title: Who can profit from personalised pricing - supplier, retailers, or consumers? Abstract: The speedy development in information technology has enabled the firms to profile consumers and serve them with personalised pricing. This study constructs a game with a supplier, dominant retailer, and weak retailer to simultaneously consider price competition and advertising competition. We find that the dominant retailer will always employ unified pricing. Regarding the weak retailer, when the cost of personalised pricing is low, it will employ personalised pricing; otherwise, it employs unified pricing. The supplier hopes that the weak retailer will employ personalised pricing to obtain higher profits. Personalised pricing improves consumer surplus, but because of the characteristics of personalised pricing itself, some consumers' interests are always harmed. It should be noted that this is single-phase research that does not consider the intertemporal situation. Journal: Int. J. of Networking and Virtual Organisations Pages: 183-210 Issue: 2 Volume: 29 Year: 2023 Keywords: personalised pricing; advertising; asymmetric competition; supplier; dominant retailer; weak retailer. File-URL: http://www.inderscience.com/link.php?id=134990 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:2:p:183-210 Template-Type: ReDIF-Article 1.0 Author-Name: E.P. Sudhakar Author-X-Name-First: E.P. Author-X-Name-Last: Sudhakar Author-Name: M. Saravanan Author-X-Name-First: M. Author-X-Name-Last: Saravanan Title: An energy-efficient task and virtual machine placement in virtualised cloud server using FY-SFLA and RMMS-DLVQ Abstract: Creating infrastructures, virtual servers, computing resources, along with devices is termed virtualisation. In this methodology, to augment resource usage along with to mitigate the total power consumption, mapping of a group of virtual machine (VM) onto a set of physical machines (PM) is performed in a data centre (DC). Nevertheless, a crucial challenge is presented by the VM allocation together with the higher energy consumption (EC) of cloud data centres (CDC). Thus, to alleviate the resource wastage along with to mitigate the DCs' EC, an effectual Fisher Yates-Shuffled frog leaping algorithm (FY-SFLA) is proposed here: 1) task feature extraction; 2) resource information extraction; 3) task separation by utilising cosine distance - K means algorithm (CD-KMA); 4) task placement in VM by employing the FY-SFLA task; 5) VM status identification by deploying random mutation monkey search deep learning vector quantisation (RMMS - DLVQ) are '5' phases comprised in the proposed methodology. Journal: Int. J. of Networking and Virtual Organisations Pages: 144-167 Issue: 2 Volume: 29 Year: 2023 Keywords: virtual machine; VM; cloud data centre; virtualisation; fishers yates; FY; shuffled frog leaping algorithm; SFLA; monkey search; MS; learning vector quantisation; LVQ. File-URL: http://www.inderscience.com/link.php?id=134992 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:2:p:144-167 Template-Type: ReDIF-Article 1.0 Author-Name: S. Arulanand Author-X-Name-First: S. Author-X-Name-Last: Arulanand Author-Name: R. Sundara Rajan Author-X-Name-First: R. Sundara Author-X-Name-Last: Rajan Author-Name: S. Prabhu Author-X-Name-First: S. Author-X-Name-Last: Prabhu Title: 2-domination number for special classes of hypercubes, enhanced hypercubes and Knödel graphs Abstract: The system is fault-tolerant if, in the case that just one of the previously employed units fails, a different chain of units is utilised in its place. Because they provide the best fault tolerance, cycle-related graphs are employed in network analysis, periodic scheduling, and surface reconstruction. This can be achieved through a mathematical concept called domination. In a graph, each node has a minimum of one neighbour in a set, and then the set is called a dominating set of a network. A dominating set with the least cardinality is the domination number of the network. In this paper, we obtain the 2-domination number of some special classes of hypercubes, enhanced hypercubes, and Knödel graphs proving that the lower bound obtained in Fink and Jacobson (1985). quite precise, and also we prove that the time complexity of the 2-domination problem for the above graphs are linear. Journal: Int. J. of Networking and Virtual Organisations Pages: 168-182 Issue: 2 Volume: 29 Year: 2023 Keywords: domination; 2-domination; hypercube; enhanced hypercube; Knödel graph; optimisation; time complexity. File-URL: http://www.inderscience.com/link.php?id=134993 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:2:p:168-182 Template-Type: ReDIF-Article 1.0 Author-Name: Minaxi Doorwar Author-X-Name-First: Minaxi Author-X-Name-Last: Doorwar Author-Name: P. Malathi Author-X-Name-First: P. Author-X-Name-Last: Malathi Title: SMNBMQR: optimisation of sleep schedules in multimedia networks via bioinspired modelling for QoS-aware routing operations Abstract: In this paper, a bioinspired model for sleep-scheduled multimedia networks is suggested in order to increase this scalability while preserving superior routing performance. The proposed model uses instantaneous node metrics such as node-to-node distance, residual energy levels, and connection quality to create initial routes. For the assessment of route fitness, these variables are paired with temporal performance measurements such as packet delivery ratio, throughput, packet priority, and temporal connection quality. In order to find the best route between a given pair of source and destination nodes, several routing options are assessed using a genetic algorithm (GA) model based on fitness value. The suggested approach is able to decrease end-to-end communication latency, energy consumption, and delay jitter because it incorporates temporal performance indicators with sleep scheduling. Additionally, when we compared several state-of-the-art methods, the suggested model can enhance network throughput and packet delivery performance. Journal: Int. J. of Networking and Virtual Organisations Pages: 211-228 Issue: 2 Volume: 29 Year: 2023 Keywords: multimedia; bioinspired computing routing; sleep scheduling; lifetime; genetic algorithm. File-URL: http://www.inderscience.com/link.php?id=134994 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:2:p:211-228 Template-Type: ReDIF-Article 1.0 Author-Name: Hamed Gheibdoust Author-X-Name-First: Hamed Author-X-Name-Last: Gheibdoust Author-Name: Shahram Gilaninia Author-X-Name-First: Shahram Author-X-Name-Last: Gilaninia Author-Name: Mohammad Taleghani Author-X-Name-First: Mohammad Author-X-Name-Last: Taleghani Title: Evaluating the influence of service quality factors in the digital hospitality industry during the COVID-19 pandemic Abstract: During the COVID-19 pandemic, digital technology has been employed in many parts of the hospitality and tourism industry. The present paper aims to evaluate the factors of the service quality (SERVQUAL) approach in the digital hospitality industry. The present research prioritised the SERVQUAL factors for the digital hospitality industry in Iran using the analytic network process (ANP). The data collection instrument was an ANP questionnaire, and data were collected in 2021. In the present research, five criteria and 20 sub-criteria were used for SERVQUAL in the field of digital hospitality. The most influencing criteria were intangibles, and among the sub-criteria, the most important one was mobile integrity. This study helps hospitality managers and policymakers to improve their use of digital services by emphasising the most influential factors in the hospitality industry. Journal: Int. J. of Networking and Virtual Organisations Pages: 18-35 Issue: 1 Volume: 28 Year: 2023 Keywords: digital hospitality; digitalisation; SERVQUAL; COVID-19; analytic network process; ANP; service quality; hospitality industry; digital technology; digital services; Iran. File-URL: http://www.inderscience.com/link.php?id=130949 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:1:p:18-35 Template-Type: ReDIF-Article 1.0 Author-Name: Xuchu Xu Author-X-Name-First: Xuchu Author-X-Name-Last: Xu Author-Name: Haofeng Han Author-X-Name-First: Haofeng Author-X-Name-Last: Han Author-Name: Bin Wu Author-X-Name-First: Bin Author-X-Name-Last: Wu Title: Value co-creation in virtual game communities: a perspective on social influence theory Abstract: The popularity of digital technologies has promoted the emergence of the online game industry. To review the relevant research, we do not simply regard online game players as consumers of game products but as value co-creators in virtual game communities. Social support theory and social influence theory are used to explore the virtual game community. Specifically, this manuscript creatively applies social influence theory to explore the factors influencing two types of value co-creation behaviours, namely player participation behaviour and citizenship behaviour, in virtual game communities. Through structural equation modelling of 491 valid questionnaires, this manuscript found that different social supports influence value co-creation among players to different degrees through three variables of social influence. The findings of this thesis provide insights into how to increase players' participation in the value co-creation process and engage them in building virtual communities. Journal: Int. J. of Networking and Virtual Organisations Pages: 53-76 Issue: 1 Volume: 28 Year: 2023 Keywords: virtual communities; value co-creation; online games; social influence theory; social support theory. File-URL: http://www.inderscience.com/link.php?id=130950 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:1:p:53-76 Template-Type: ReDIF-Article 1.0 Author-Name: Nilmini Wickramasinghe Author-X-Name-First: Nilmini Author-X-Name-Last: Wickramasinghe Author-Name: Rima Gibbings Author-X-Name-First: Rima Author-X-Name-Last: Gibbings Title: Using digital health to support superior preparedness to enable better preparedness and readiness to combat pandemics: a scoping review Abstract: The COVID-19 pandemic that dominated the world in 2020 causing millions of deaths, severe illness, immense chaos and stress to healthcare systems and services not to mention detrimental effects to economies and the lives of all, has served to highlight key vulnerabilities in most countries; namely, those around not being prepared. Based on the world's experiences through 2020, it has been noted by the WHO that a better state of preparedness would have enabled a better state of readiness to combat the COVID-19 pandemic and thus not only significantly reduce the loss of life but also the catastrophic impacts to the economy and the lives of all people. This paper performs a scoping review to identify and propose an appropriate approach of being better prepared for pandemics and other emergency scenarios. Journal: Int. J. of Networking and Virtual Organisations Pages: 1-15 Issue: 1 Volume: 29 Year: 2023 Keywords: clusters of pneumonia; vulnerable populations; comorbidities; missing data. File-URL: http://www.inderscience.com/link.php?id=134280 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:1:p:1-15 Template-Type: ReDIF-Article 1.0 Author-Name: Iman Karam I.M. Ashmawy Author-X-Name-First: Iman Karam I.M. Author-X-Name-Last: Ashmawy Title: Does remote work promote shared leadership in public organisations? Abstract: With the outbreak of the COVID-19 pandemic and the imposed lockdowns, various public organisations adopted remote work for safety measures. However, many studies warn that remote work might make the employees feel isolated and make it difficult for the leadership to observe and evaluate employee performance. These challenges were preceded by an increased emphasis on informal, lateral, or collective styles of leadership, such as shared leadership. Therefore, this paper seeks to investigate the extent to which remote work promotes shared leadership. By disseminating a questionnaire to <i>N</i> = 90 employees working at a central public organisation (CPO) and statistically analysing it, the findings reveal surprising conclusions that highlight a positive correlation between remote work and shared leadership, including its components of bottom-up leadership, collective assumption of responsibility, and reciprocal interdependence, respectively. Journal: Int. J. of Networking and Virtual Organisations Pages: 38-54 Issue: 1 Volume: 29 Year: 2023 Keywords: remote work; shared leadership; collective assumption of responsibility; reciprocal interdependence; bottom-up leadership. File-URL: http://www.inderscience.com/link.php?id=134282 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:1:p:38-54 Template-Type: ReDIF-Article 1.0 Author-Name: Musfiah Saidah Author-X-Name-First: Musfiah Author-X-Name-Last: Saidah Author-Name: Purwadi Purwadi Author-X-Name-First: Purwadi Author-X-Name-Last: Purwadi Title: An actor-network model for developing data sovereignty: evidence from Indonesia Abstract: This study aimed to understand and form an actor-network model for realising data sovereignty based on various evidence of problems in Indonesia. In addition, this study used the concept of data sovereignty to understand information processing practices, laws, and the needs of a country. This study used a qualitative approach using multi-methods, which looked at the heterogeneity of qualitative methods using case study research strategies and action research with soft system methodology (SSM). The findings of this study offered an actor-network model in realising data sovereignty based on evidence-based problems in Indonesia. A precise classification between private and public data is required to implement data sovereignty. The realisation of data sovereignty required the support of various stakeholders: the government, parliament, the private sector, academia, the community, and non-human actors. Data sovereignty is oriented towards economic value and data security. Then, good regulation to ensure data security is the primary pretension. Journal: Int. J. of Networking and Virtual Organisations Pages: 55-72 Issue: 1 Volume: 29 Year: 2023 Keywords: actor-network model; actor-network; data sovereignty; communication applications; government; privacy; Indonesia; data; sovereignty; communication. File-URL: http://www.inderscience.com/link.php?id=134283 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:1:p:55-72 Template-Type: ReDIF-Article 1.0 Author-Name: Luuk P.A. Simons Author-X-Name-First: Luuk P.A. Author-X-Name-Last: Simons Title: Health 2050: faster cure via bioinformatics and quantified self; a design analysis Abstract: Four areas make up 75% of our healthcare costs: cardio-, onco-, neuro- and metabolic diseases. These are largely preventable, even reversible. Instead, they are currently often 'managed' and made chronic, not cured. This is too costly. Research is showing new opportunities for enhancing our body's self-repair in a matter of hours or days. Our research question: what could be an intervention- and bio-feedback portfolio to promote health self-repair within hours or days? There are large cross-domain differences regarding: intervention aims, (self-)measurement options, focus on symptoms vs. causes, plus degree of attention for health self-management. Given recent research into rapid cure, we advise advanced daily bioinformatics feedback, using molecular biomarkers. This creates a quantified self 'endoself', showing key biological opportunities for cure and self-repair. Thus, we shift from the current 'antibiotics/external fix' paradigm of healthcare to a 'wound healing' paradigm, improving use of resources in health. Journal: Int. J. of Networking and Virtual Organisations Pages: 36-52 Issue: 1 Volume: 28 Year: 2023 Keywords: health; self-management; quantified self; non-communicable diseases; NCDs; bioinformatics; service design; personal medicine. File-URL: http://www.inderscience.com/link.php?id=130957 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:1:p:36-52 Template-Type: ReDIF-Article 1.0 Author-Name: Ping Wang Author-X-Name-First: Ping Author-X-Name-Last: Wang Author-Name: Wen Chen Author-X-Name-First: Wen Author-X-Name-Last: Chen Title: The influences of the characteristics of opinion leaders on consumer purchase intention in a mobile e-commerce webcast context Abstract: The mobile e-commerce webcast has great commercial value through the way of live streaming to sell products, place advertisements, and create an ecosystem in conjunction with other industries to make capital available. Based on the stimuli-organism-response (SOR) model, in a sample of 393 consumers in China, multiple regression analysis and bootstrap are used to estimate the influences of the characteristics of opinion leaders on consumer purchase intention in the context of mobile e-commerce webcast. The results show that the characteristics of opinion leaders exert a significant positive influence on consumer purchase intention and flow experience; flow experience has a significant positive influence on consumer purchase intention; and flow experience has partial mediating effects between the characteristics of opinion leaders and consumer purchase intention. The findings provide support for the research model. Furthermore, practical implications are provided for long-term development of mobile e-commerce live operators. Journal: Int. J. of Networking and Virtual Organisations Pages: 1-17 Issue: 1 Volume: 28 Year: 2023 Keywords: opinion leaders; consumer purchase intention; flow experience; mobile e-commerce webcast; SOR model. File-URL: http://www.inderscience.com/link.php?id=130958 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:1:p:1-17 Template-Type: ReDIF-Article 1.0 Author-Name: T. Sarath Babu Author-X-Name-First: T. Sarath Author-X-Name-Last: Babu Author-Name: Penke Satyanarayana Author-X-Name-First: Penke Author-X-Name-Last: Satyanarayana Author-Name: S. Nagaraja Rao Author-X-Name-First: S. Nagaraja Author-X-Name-Last: Rao Title: Exploration of cognitive radio network with the integrated optimisation of channel allocation and power control by hybrid algorithm Abstract: Cognitive radio is one of wireless communications where the involving communication channels are detected through a transceiver. Spectrum allocation is a key challenge in the research on cognitive radio networks (CRNs). The conventional studies are focused on providing low-complexity solutions to find the power allocation to enhance energy efficiency and reduce the interference of the primary user and thus, satisfying the secondary users' minimum rate requirements. Thus, there is a need to introduce joint optimisation of channel allocation and power control in CRN. This is achieved by a new heuristic algorithm with the binary bat-reptile search algorithm (BB-RSA). This integrated mechanism is formulated by solving the multi-objective function regarding functions like throughput, outage probability, and Ergodic capacity. The heuristic algorithm is proposed to realise the best channel and power allocation in CRN. Extensive simulation results are presented to demonstrate the performance of the proposed scheme. Journal: Int. J. of Networking and Virtual Organisations Pages: 77-101 Issue: 1 Volume: 28 Year: 2023 Keywords: cognitive radio networks; CRNs; channel allocation and power control optimisation; throughput; outage probability; Ergodic capacity; binary bat-reptile search algorithm; BB-RSA. File-URL: http://www.inderscience.com/link.php?id=130959 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:1:p:77-101 Template-Type: ReDIF-Article 1.0 Author-Name: Christopher P. Furner Author-X-Name-First: Christopher P. Author-X-Name-Last: Furner Author-Name: John R. Drake Author-X-Name-First: John R. Author-X-Name-Last: Drake Author-Name: Ravi Paul Author-X-Name-First: Ravi Author-X-Name-Last: Paul Title: A longitudinal study of the interplay between team dynamics and media use in virtual teams Abstract: Virtual teamwork has grown exponentially, particularly following shelter-in-place orders accompanying the COVID-19 pandemic. The influence of trust on a variety of team dynamics is well studied, and investigation into the influence of media use on team dynamics is emerging; however, many such studies are cross-sectional. A longitudinal study of team dynamics and media use is conducted using 235 students in MBA case analysis teams. Findings support established relationships between trust and impressions of teamwork and, ultimately, performance. Detailed findings indicate that during early phases, video conferencing increases trust and performance; during middle phases, higher levels of trust are associated with the use of texting; and during later phases, the use of e-mail increases performance. These findings are discussed in terms of channel expansion theory and the virtual teams paradigm. Journal: Int. J. of Networking and Virtual Organisations Pages: 16-37 Issue: 1 Volume: 29 Year: 2023 Keywords: virtual teams; team dynamics; media selection; channel expansion theory; CET. File-URL: http://www.inderscience.com/link.php?id=134300 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:1:p:16-37 Template-Type: ReDIF-Article 1.0 Author-Name: Chanchal Ahlawat Author-X-Name-First: Chanchal Author-X-Name-Last: Ahlawat Author-Name: Rajalakshmi Krishnamurthi Author-X-Name-First: Rajalakshmi Author-X-Name-Last: Krishnamurthi Title: Towards smart technologies with integration of the internet of things, cloud computing, and fog computing Abstract: In the recent era of technology, the internet of things (IoT) plays a tremendous role in enhancing the quality of human life through smart devices and sensing the real-world environment. IoT aims to interconnect anything from anywhere via the internet. The existing literature lacks in providing deeper research insight toward a broader perspective of integrating IoT, cloud computing (CC), and fog computing (FC). Hence, this paper aims to provide a comprehensive review of integrating these main emerging technologies and four major objectives are addressed. The first objective identifies the primary characteristics of IoT to solve real-life problems. The second objective addresses the issues that necessitate the integration of IoT with other emerging technologies. The third objective involves how the integration of IoT with CC elevates the scope of providing a solution to real-life problems. The final objective addresses the limitations of the integration of IoT with CC and how FC overcomes these limitations. Journal: Int. J. of Networking and Virtual Organisations Pages: 73-124 Issue: 1 Volume: 29 Year: 2023 Keywords: internet of things; IoT; cloud computing; CC; fog computing; FC; mobile cloud computing; MCC; mobile edge computing; MEC. File-URL: http://www.inderscience.com/link.php?id=134304 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:29:y:2023:i:1:p:73-124 Template-Type: ReDIF-Article 1.0 Author-Name: Junmei Guo Author-X-Name-First: Junmei Author-X-Name-Last: Guo Title: Evaluation and analysis of classroom teaching quality of art design specialty based on DBT-SVM Abstract: Evaluating the quality of classroom teaching in higher education can improve teachers' teaching, but the evaluating results are currently inaccurate. The study combines the binary tree support vector machine (BT-SVM) and the Euclidean distance method to obtain the distance binary tree support vector machine (DBT-SVM) algorithm. The performance of DBT-SVM algorithm is tested and compared with one versus one (OVO) algorithm and one versus rest (OVR) algorithm. The results show that the accuracy of the DBT-SVM is 92.2% and the test time is 0.02 s; it is superior to the traditional algorithms. In the empirical analysis of the evaluation model, the accuracy rate of the DBT-SVM algorithm model is 97.85%, which is superior to TW-SVM and traditional algorithm models. The results show that the performance of the optimised DBT-SVM algorithm has greatly improved the accuracy and test time of the traditional SVM algorithm. Journal: Int. J. of Networking and Virtual Organisations Pages: 106-121 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: teaching quality evaluation; binary tree; Euclidean distance method; support vector machine; binary tree support vector machine; BT-SVM; distance binary tree support vector machine; DBT-SVM; one versus one; OVO. File-URL: http://www.inderscience.com/link.php?id=133833 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:106-121 Template-Type: ReDIF-Article 1.0 Author-Name: Jing Wang Author-X-Name-First: Jing Author-X-Name-Last: Wang Title: The application of clustering algorithms in a new model of knitted garment talent training in the context of sustainable development Abstract: Under the concept of sustainable development, the innovation and development of the knitted garment industry is crucial. In order to enhance the core competitiveness of the knitted garment industry, the study proposes a talent training strategy for the knitted garment industry based on a clustering algorithm, and constructs a talent-training model. The clustering algorithm showed a significant clustering effect, with a clustering accuracy of 93.66% in the real dataset. The knitwear talent development model obtained through the clustering analysis was applied in practice, and the application of talent development was able to significantly increase the proportion of elite talent in the company. The above results show that in the knitted garment industry under the concept of sustainable development, cluster analysis can effectively build a talent-training program, which is of great value to the sustainable development of the knitted garment industry and the production industry. Journal: Int. J. of Networking and Virtual Organisations Pages: 139-153 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: sustainable development; clustering algorithm; knitwear; talent development. File-URL: http://www.inderscience.com/link.php?id=133835 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:139-153 Template-Type: ReDIF-Article 1.0 Author-Name: Shiwei Zhang Author-X-Name-First: Shiwei Author-X-Name-Last: Zhang Title: Research on government network public opinion monitoring algorithm under the background of sustainable smart government Abstract: It is very necessary for the government to strengthen the supervision of network information. Considering the problems of over fitting and gradient disappearance in the traditional bi directional long short-term memory (BiLSTM) network, the regularisation method is used to adjust the input weight of the model. At the same time, 333 functions is used to replace tanh activation function to build a government network public opinion monitoring model of double-layer long short-term memory network (RLSTM). The model performance test results show that in dataset type 1, the public opinion prediction accuracy is 0.993, and in dataset type 2, the public opinion prediction accuracy is 0.982, and the prediction performance is the best. At the same time, the improved RLSTM model also has excellent performance in the test of model convergence effect and error performance. The research content is of great significance to strengthen the security supervision of network information. Journal: Int. J. of Networking and Virtual Organisations Pages: 231-246 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: smart government; RLSTM model; public opinion; monitoring. File-URL: http://www.inderscience.com/link.php?id=133844 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:231-246 Template-Type: ReDIF-Article 1.0 Author-Name: Jingjing Gong Author-X-Name-First: Jingjing Author-X-Name-Last: Gong Author-Name: Hongwen Han Author-X-Name-First: Hongwen Author-X-Name-Last: Han Author-Name: Zhen Lv Author-X-Name-First: Zhen Author-X-Name-Last: Lv Title: Construction of a GA-RBF-based early warning model for corporate financial risk in the context of sustainable development Abstract: Financial risk indicators will have a negative impact on the development planning of enterprises, so the research introduces the theory of genetic algorithm. The result is that the overall performance of the model based on GA-RBF is superior to that of the model based on BF, CNN and RBF. GA-RBF model reaches a stable state when the number of training is 120, and the speed is significantly faster than the other three models. The error value of GA-RBF model is significantly lower than other model, and the error reduction speed is also faster. The time and memory of the four models increase with the increase of the number of samples, but the time and memory of GA-RBF model is less than the other three models. The highest prediction accuracy of GA-RBF model is 91.25%, and the highest prediction accuracy of RBF neural network is 64.5%. Journal: Int. J. of Networking and Virtual Organisations Pages: 184-198 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: sustainable development; GA-RBF; corporate finance; risk warning. File-URL: http://www.inderscience.com/link.php?id=133845 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:184-198 Template-Type: ReDIF-Article 1.0 Author-Name: Xianghong Yin Author-X-Name-First: Xianghong Author-X-Name-Last: Yin Title: Application analysis of data mining based on improved decision tree in English flipped classroom teaching Abstract: This study aims to analyse the application of data mining based on improve decision in English flipped classroom teaching. The experimental results show that the improved C4.5 algorithm had a better performance than ID3 algorithm and C4.5 algorithm and CART algorithm. In terms of accuracy rate, the four algorithms can be ranked as improved C4.5 algorithm, C4.5 algorithm, ID3 algorithm, and CART algorithm from high to low. Moreover, the improved C4.5 algorithm had the lowest error rate among the four algorithms. Under the same number of training samples, the improved C4.5 algorithm takes the least time at the least memory cost. Therefore, the improved C4.5 algorithm is adopted to construct a data mining model for English flipped classroom teaching and promote the research on English flipped classroom teaching. Journal: Int. J. of Networking and Virtual Organisations Pages: 171-183 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: improved decision tree; data mining; English flipped classroom; C4.5 algorithm. File-URL: http://www.inderscience.com/link.php?id=133848 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:171-183 Template-Type: ReDIF-Article 1.0 Author-Name: Yue Feng Author-X-Name-First: Yue Author-X-Name-Last: Feng Title: An application of neural network algorithm model based on improved multi-expression programming in English language education practice Abstract: In the field of English education, neural network algorithm can effectively predict and evaluate teaching, and significantly improve the quality of education and teaching. Therefore, a neural network English teaching evaluation prediction model based on multi expression programming is proposed. Through the research on neural network and genetic algorithm (GA), it is found that flexible neural tree cannot optimise parameters and results at the same time. Therefore, a neural network algorithm model (MEP) based on multi expression programming is proposed to solve the problem, and the MEP-NN English teaching evaluation model is constructed by optimising the model parameters with evolutionary algorithm. The model is applied to the English teaching process to achieve the evaluation of English teaching quality. The results show that in the mean square error performance test of multiple algorithms, achieving convergence after 500 iterations, with an MSE value of 0.02 and the best error performance; in the English class comprehensive quality prediction, the proposed MEP-NN algorithm has the best prediction accuracy, with a prediction mean of 86.56 points, closest to the actual value of 86 score, with a prediction accuracy of 94.56%. This shows that the proposed MEP-NN algorithm has excellent performance. Journal: Int. J. of Networking and Virtual Organisations Pages: 281-300 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: neural networks; multi-expression programming; English language education; prediction. File-URL: http://www.inderscience.com/link.php?id=133860 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:281-300 Template-Type: ReDIF-Article 1.0 Author-Name: Li Ling Author-X-Name-First: Li Author-X-Name-Last: Ling Title: A study on the development of English reading skills in the MOOC model of English language teaching Abstract: This study proposes a personalised intelligent reading resource recommendation method based on MOOC mode. This method uses a deep belief network (DBN) model to extract students' reading interests and other related data features, and uses the K-means algorithm to classify users' interests. The model is applied to a personalised recommendation system in the MOOC environment. When the training set accounts for 100%, 75%, 50%, and 25% of the total dataset, the root mean square errors of the recommendation results of the DBN algorithm are 78%, 83%, 88%, and 96%, respectively. During the training process, the convergence speed of the DBN algorithm is significantly faster, with a minimum root mean square error value of 0.805. In the evaluation of recommendation effectiveness under different indicators, DBN performs the best, indicating that the model can adapt to various situations and has great practical application value. Journal: Int. J. of Networking and Virtual Organisations Pages: 318-336 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: MOOC; English teaching; reading ability; personalised recommendation; deep belief network; DBN. File-URL: http://www.inderscience.com/link.php?id=133861 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:318-336 Template-Type: ReDIF-Article 1.0 Author-Name: Qiang Wu Author-X-Name-First: Qiang Author-X-Name-Last: Wu Title: Research on text data sentiment analysis algorithm integrating transfer learning and hierarchical attention network Abstract: The rapid development of the internet has changed the way people express their opinions and emotions. How to use high-performance sentiment analysis algorithms for practical auxiliary product recommendation and public opinion analysis has become a research hotspot. This research proposes a text data sentiment analysis algorithm that integrates transfer learning and hierarchical attention network, and conducts sentiment analysis on single domain and cross domain text data and verifies the effectiveness of the algorithm. The results show that the TLHANN algorithm has an accuracy of 0.85 in IMDB2 data samples, which is higher than other algorithms. In the field of books and DVDs, the accuracy of this algorithm is 0.83, while the other algorithms are 0.826 and 0.828, respectively, which are lower than the FMCSC algorithm. This verifies the effectiveness of the cross domain text sentiment analysis FMCSC algorithm and further verifies its optimal performance. Journal: Int. J. of Networking and Virtual Organisations Pages: 301-317 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: transfer learning; hierarchical attention; sentiment analysis; TLHANN algorithm; FMCSC algorithm. File-URL: http://www.inderscience.com/link.php?id=133862 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:301-317 Template-Type: ReDIF-Article 1.0 Author-Name: Bin Li Author-X-Name-First: Bin Author-X-Name-Last: Li Title: Optimisation of UCB algorithm based on cultural content orientation of film and television in the digital era Abstract: To improve the effect of the upper confidence bound (UCB) algorithm in the recommendation of online courses of film and television culture, the paper proposes the recommendation method with time-varying Linucb. Firstly, the time-varying Linucb is introduced, and the UCB is optimised by using the attention mechanism and the short-term and short-term memory network. The results show that the recommendation accuracy of the improved model reaches up to 93%, and the novelty is basically stable at 70%. Compared with UCB, the average course viewing time of users has been extended by two hours, and the average course registration rate has remained stable at over 84%. This indicates that the improved recommendation model has excavated the diverse learning needs of users and can provide accurate course recommendation services for users, which is conducive to optimising the effectiveness of film and television cultural education. Journal: Int. J. of Networking and Virtual Organisations Pages: 265-280 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: film and television culture; digital era; UCB; attention mechanism; long- and short-term memory network. File-URL: http://www.inderscience.com/link.php?id=133865 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:265-280 Template-Type: ReDIF-Article 1.0 Author-Name: Jing Qiu Author-X-Name-First: Jing Author-X-Name-Last: Qiu Author-Name: Feng Gao Author-X-Name-First: Feng Author-X-Name-Last: Gao Title: Study on active sleeping node detection method in sensor network based on multi-dimensional sliding window Abstract: To overcome the problems of low coverage and detection accuracy in traditional detection methods, a multidimensional sliding window based active sleep node detection method for sensor networks is proposed. Firstly, we set up an active sleep node simulator and controller in the sensor network space to determine the active sleep range. Secondly, we design a multidimensional sliding window algorithm to determine anomalies in the transmission link by calculating the standard deviation of sensing information in the sliding window. Finally, the total length of data transmission is dimensionally transformed to achieve reliable detection of active sleep nodes. The experimental results show that the coverage rate of the detection results of this method is closer to 1, and its detection accuracy remains between 94.84% -97.32%, and the detection process time remains between 1.72 s-232 s. It has the advantages of strong reliability and high efficiency in applications. Journal: Int. J. of Networking and Virtual Organisations Pages: 337-347 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: sensor networks; active sleep node; node detection; multi dimensional sliding window algorithm; sliding window; active sleep range; standard deviation. File-URL: http://www.inderscience.com/link.php?id=133867 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:337-347 Template-Type: ReDIF-Article 1.0 Author-Name: Fei Huang Author-X-Name-First: Fei Author-X-Name-Last: Huang Author-Name: Meiqun Liao Author-X-Name-First: Meiqun Author-X-Name-Last: Liao Title: Analysis of the application of HMM algorithm in teaching musical note feature recognition in universities Abstract: With the rapid development of music education and information technology in colleges and universities, how to improve the efficiency of teachers' teaching in current music courses has increasingly become a focus of public attention. This study aims to propose an HMM algorithm based on the application of music note feature recognition teaching in colleges and universities. The experimental results show that the HMM algorithm is used in the music frequency sample signal after pre-processing, and its target accuracy is reached after 20 training sessions. Comparing the HMM algorithm with the other two algorithms, the results show that its correct rate is about 99.56%, and the probability of occurrence of insertion error and elimination error is 0.52% and 2.58%, which is better than the other two algorithms. In summary, it shows that the research proposed HMM algorithm has some practical value and relevance to the teaching of music in colleges and universities. Journal: Int. J. of Networking and Virtual Organisations Pages: 214-230 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: HMM algorithm; music teaching; feature recognition; fundamental frequency recognition method; pitch class profile; PCP. File-URL: http://www.inderscience.com/link.php?id=133868 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:214-230 Template-Type: ReDIF-Article 1.0 Author-Name: Yueying Xiao Author-X-Name-First: Yueying Author-X-Name-Last: Xiao Title: AGA-BP algorithm for the evaluation model of teaching quality of dance drama performance Abstract: Firstly, the evaluation system was determined, then the AGA and BP neural network algorithms were improved, and finally the entropy weight method was used to construct the dance drama performance teaching quality evaluation model. The optimal hidden layer node of the BP algorithm is 5 and the maximum number of iterations is 120. The corresponding MSE values of the two neural network algorithms, BP and AGA-BP, are 0.0486 and 0.0246 respectively at the maximum number of 120 iterations. The number of convergence of the AGA-BP algorithm is about 6; the convergence value of the sum of squared errors is 0.21, with a 75% improvement in convergence speed and an 80% reduction in the average sum of squared errors. The prediction results of the dance performance quality evaluation show that the prediction accuracy of the AGA-BP prediction model ranges from 0.97 to 1.00. Journal: Int. J. of Networking and Virtual Organisations Pages: 199-213 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: adaptive genetic algorithm; AGA; BP; teaching dance performance; quality assessment. File-URL: http://www.inderscience.com/link.php?id=133869 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:199-213 Template-Type: ReDIF-Article 1.0 Author-Name: Mengran Niu Author-X-Name-First: Mengran Author-X-Name-Last: Niu Title: Research on tennis-assisted teaching assessment technology based on improved dense trajectory algorithm Abstract: With the continuous development of artificial intelligence technology, tennis robots begin to enter people's lives. This study proposes a tennis-assisted teaching evaluation method based on improved dense trajectory algorithm. The results show that the best recognition effect is obtained under the division method when the division parameters <i>n<SUB align="right"><SMALL>σ</SMALL></SUB></i> and <i>n</i><SUB align="right"><SMALL>Γ</SMALL></SUB> of non-fixed-length trajectories are 2 and 3 respectively. The calculation effect obtained by Chebyshev distance formula is better, and the distance between various types of actions is mainly distributed around 0.2, and the actual distance existing between them and the standard action is smaller. The BD rate of 4K video increases from 11.45% to 32.98%, while that of 8K video increases from 1.82% to 7.61%. The more the number of tile divided by the system, the more the performance is lost, and globally, the coding performance affected by the optimised MCTS is acceptable. From the global view of the test, it is still possible to accept the transmission delay caused by the faster code stream fusion to the system. Journal: Int. J. of Networking and Virtual Organisations Pages: 154-170 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: dense trajectory; tennis; auxiliary teaching; adaptive transmission; motion capture. File-URL: http://www.inderscience.com/link.php?id=133870 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:154-170 Template-Type: ReDIF-Article 1.0 Author-Name: Yantai Zhang Author-X-Name-First: Yantai Author-X-Name-Last: Zhang Title: Application of improved clustering algorithm in precision poverty auditing - an example from region D Abstract: In order to accurately improve the audit of poor households in poverty alleviation projects, as well as the unreasonable parameter setting and low clustering accuracy of clustering analysis algorithm in its application. The study proposes a KLS-DBSCAN cluster analysis algorithm. The algorithm first uses kernel function estimation to determine a reasonable interval for the neighbourhood and the minimum number of nodes then uses the data local density characteristics to determine the number of clusters according to the parameter values within the reasonable interval, followed by the maximum contour coefficient to determine the optimal parameters. The optimal combination of hyperparameters for the KLS-DBSCAN cluster analysis algorithm is (0.25, 3), with 42 outlier points and nine clusters. Compared with the other three clustering analysis algorithms, the number of outliers in clusters is about 20. This research providing possibilities and technical support for the proper implementation of precision poverty alleviation audit work. Journal: Int. J. of Networking and Virtual Organisations Pages: 247-264 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: DBSCAN; precision poverty audit; density clustering; adaptive; parameter search. File-URL: http://www.inderscience.com/link.php?id=133871 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:247-264 Template-Type: ReDIF-Article 1.0 Author-Name: Xifeng Qin Author-X-Name-First: Xifeng Author-X-Name-Last: Qin Title: Research on the application of deep learning algorithm based PS design software technology in oil painting teaching Abstract: More and more minors are cultivating oil painting as a hobby. Beginners of oil painting often cannot correctly identify optimised styles and similar painting objects due to the lack of professional knowledge and insufficient aesthetic ability of oil painting. This research addresses this problem by designing a shared convolutional neural network and an improved global convolutional neural network, and combining the two with Photoshop (short name: PS) software processing steps to compose an intelligent oil painting recognition model for beginner teaching. The experimental results of model performance testing show that the recognition model designed in this study has lower training and computation speed. However, the recognition accuracy of various images in the test sample set is higher than that of the comparison oil painting recognition model. Which is significantly higher than the oil painting recognition model built based on GoogleNet, visual geometry group (VGG) and AlexNet neural network algorithms. Journal: Int. J. of Networking and Virtual Organisations Pages: 122-138 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: deep learning; PS design software; oil painting teaching; convolutional neural network. File-URL: http://www.inderscience.com/link.php?id=133872 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:122-138 Template-Type: ReDIF-Article 1.0 Author-Name: Yan Yang Author-X-Name-First: Yan Author-X-Name-Last: Yang Title: Research on long- and short-term music preference recommendation method integrating music emotional attention Abstract: In order to improve the effect of user music personalised recommendation, a hybrid music personalised recommendation model based on attention mechanism and multi-layer LSTM is proposed from the perspective of user music emotion and behaviour data. Using multi-layer LSTM to mine users' long-term and short-term music preferences, the model can analyse users' music emotional attributes in combination with attention mechanism. The research results show that the recommendation accuracy of the AM-LSTPM model is 97.86%, the recall rate is 98.91%, and the NDCG@10 values of the model on the two datasets are 0.5771 and 0.5437, which can effectively provide users with targeted personalised music recommendation services. The research, based on the modelling of users' long-term and short-term music preferences and integrating users' music emotional attention analysis, provide users with high-quality targeted music recommendation services, and have important value in promoting the improvement of music streaming media service quality. Journal: Int. J. of Networking and Virtual Organisations Pages: 381-397 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: long short-term memory; LSTM; attention mechanism; music; personalised recommendation; emotion. File-URL: http://www.inderscience.com/link.php?id=133873 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:381-397 Template-Type: ReDIF-Article 1.0 Author-Name: Peng Liu Author-X-Name-First: Peng Author-X-Name-Last: Liu Title: Application of virtual reality and multimedia integration in piano teaching of sound education major in colleges and universities Abstract: The research has organically integrated VR and multimedia technology, built a corresponding piano teaching platform, and verified its effectiveness through experiments. The experimental results show that the classification effect, classification accuracy and recognition rate have been significantly enhanced after the internal selection algorithm of VR-MM is improved. Among them, the VLRAMM-BPNN algorithm, combining the two improved algorithms with BPNN, has the best performance, the highest coincidence between actual and predicted classification results, the highest classification accuracy of 95.93%, and the recognition rate is 21.6% higher than that of BPNN. According to the overall performance test of VR-MM, both the response speed and various stress tests have achieved the desired results. When the number of people is set at 10,000, the pressure has also reached the bottleneck, fully meeting the actual needs of piano teaching. To sum up, the performance of VR-MM has achieved the expected effect. Journal: Int. J. of Networking and Virtual Organisations Pages: 430-444 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: virtual reality; multimedia; audio education major; piano teaching. File-URL: http://www.inderscience.com/link.php?id=133874 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:430-444 Template-Type: ReDIF-Article 1.0 Author-Name: Lianmei Deng Author-X-Name-First: Lianmei Author-X-Name-Last: Deng Title: Analysis and application of knowledge points in English network course teaching by using PageRank Abstract: The research uses PageRank algorithm to calculate the <i>R</i> value of English network teaching knowledge points, and analyses its changes through experiments to give the focus of teaching knowledge points. The results show that learners' enthusiasm for learning English online courses fluctuates significantly, and their final scores are affected by the number of days of study, with the highest pass rate reaching 76.6%. Learners hit the most at the beginning of learning English, which decreased over time, up to 8,650 times. At the same time, the accuracy and recall of PageRank algorithm in knowledge point analysis are at a high level, with the accuracy reaching 88.1%. Using PageRank algorithm to calculate the <i>R</i> value of knowledge points can enable teachers to adjust teaching methods and strategies according to their changes, and learners can also master the learning focus, which is highly practical in the analysis of knowledge points. Journal: Int. J. of Networking and Virtual Organisations Pages: 415-429 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: PageRank algorithm; network course teaching; knowledge point analysis; theoretical support. File-URL: http://www.inderscience.com/link.php?id=133875 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:415-429 Template-Type: ReDIF-Article 1.0 Author-Name: Haifeng Shi Author-X-Name-First: Haifeng Author-X-Name-Last: Shi Author-Name: Ling Shang Author-X-Name-First: Ling Author-X-Name-Last: Shang Title: Research on big data personalised recommendation model based on deep reinforcement learning Abstract: In order to mine the user's preference and interest from the user's historical behaviour in the big data to make a personalised recommendation, a DRR model is constructed based on deep reinforcement learning, and the performance of the DRR model is analysed through experiments. The results showed that the DRR model had a higher effect than other comparable models in the offline experimental evaluation, and the DRR-att value was the highest, reaching 0.9025. In the online simulation experiment, the average DRR-att value was the highest reward rate, reaching 0.7466. In general, the DRR model had better analysis ability and strong dynamic modelling ability and was good at using long-term rewards for decision making. In the parameter analysis experiment, the <i>T</i> value reached ten points. At the same time, the user state expression module can improve the accuracy of the DRR model and is effective in actual user personalised recommendations. Journal: Int. J. of Networking and Virtual Organisations Pages: 364-380 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: deep reinforcement learning; personalised recommendation; dynamic modelling; effectiveness. File-URL: http://www.inderscience.com/link.php?id=133876 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:364-380 Template-Type: ReDIF-Article 1.0 Author-Name: Jun Chen Author-X-Name-First: Jun Author-X-Name-Last: Chen Title: Application research of improved Apriori algorithm in teaching evaluation of mobile platform for elderly education Abstract: How to improve the teaching level of elderly education is of great practical significance to the current 'elderly' countries and regions. In this study, we improve the Apriori algorithm to analyse the teaching evaluation data, and test the performance and apply the analysis. The results show that the minimum and maximum runtime of the traditional Apriori algorithm is 23 ms and 177 ms respectively, while the minimum and maximum runtime of the improved Apriori algorithm is 17 ms and 163 ms respectively, which indicates a better classification performance in data mining. The basic information of teachers was analysed to show the association of teachers' titles, education and age. Compared with other algorithms, the improved Apriori algorithm saves running time to a certain extent, has better accuracy and precision than other algorithms, and can achieve effective analysis of teaching evaluation data on the mobile platform for senior education. Journal: Int. J. of Networking and Virtual Organisations Pages: 348-363 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: Apriori algorithm; data mining; teaching evaluation; mobile platform; elderly education; association rules. File-URL: http://www.inderscience.com/link.php?id=133877 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:348-363 Template-Type: ReDIF-Article 1.0 Author-Name: Linna Huang Author-X-Name-First: Linna Author-X-Name-Last: Huang Title: The application and research of double-layer music emotion classification model based on random forest algorithm in digital music Abstract: It is urgent to solve the problem of music emotion classification. The stochastic forest algorithm is easy to operate and performs better than other single-layer classification models. Aiming at the problems of feature extraction and classification in conventional music emotion classification methods, music features are divided into long-term features and short-term features, and a two-layer music emotion classification model integrating a random forest (RF) algorithm is designed. The experimental results showed that the SVM model using the Gaussian radial basis kernel function had the highest classification accuracy of 90.78% in training the SVM model. The overall classification accuracy of the two-layer music emotion classification model was 98.92%, the recall rate was 97.63%, and its indicators in different emotion categories were the highest, with an average F1 value of 0.919. To sum up, the two-layer music emotion classification model based on the RF algorithm proposed in the research has excellent recognition and classification capabilities. Journal: Int. J. of Networking and Virtual Organisations Pages: 445-460 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: random forest; RF; emotional classification; double layer model; music characteristics; SVM. File-URL: http://www.inderscience.com/link.php?id=133878 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:445-460 Template-Type: ReDIF-Article 1.0 Author-Name: Hongxia Zhang Author-X-Name-First: Hongxia Author-X-Name-Last: Zhang Title: Construction and application of English teachers' intelligent classroom teaching ability training mode integrating MOOC and flipped classroom Abstract: Supported by internet technology, the English teaching mode integrating MOOC and flipped classroom is widely welcomed. The commonly used evaluation methods of teaching effect cannot meet the requirements of formative evaluation. Therefore, a teaching evaluation method based on RBF is constructed. Aiming at the defects of RBF in data processing, the optimised RBF based on K-means clustering algorithm is proposed. The findings indicate that the training effectiveness of the improved RBF evaluation method is 0.99. In the intelligent English teaching mode integrating MOOC and flipped classroom, the standard deviation of the total score of students is 7.186. Therefore, the teaching impact assessment methodology based on improved RBF can better assess the English instruction integrating MOOC and flipped classroom, and optimise English teachers' teaching methods. Journal: Int. J. of Networking and Virtual Organisations Pages: 398-414 Issue: 2/3/4 Volume: 28 Year: 2023 Keywords: massive open online courses; MOOC; flipped classroom; teaching ability; radial basis function; RBF; K-means clustering. File-URL: http://www.inderscience.com/link.php?id=133885 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijnvor:v:28:y:2023:i:2/3/4:p:398-414