Template-Type: ReDIF-Article 1.0
Author-Name: Sashank Sridhar
Author-X-Name-First: Sashank
Author-X-Name-Last: Sridhar
Author-Name: Siddartha Mootha
Author-X-Name-First: Siddartha
Author-X-Name-Last: Mootha
Title: Stock market manipulation detection using feature modelling with hybrid recurrent neural networks
Abstract:
A stock market is a potent platform which handles a large of number of transactions within a second. Keeping track of every single transaction is a daunting task for regulatory bodies. The objective of a regulatory body is to ensure a fair trading environment and to verify that the price of a stock is not being manipulated. This paper proposes a hybrid stacked artificial neural network and recurrent neural network to model the static and dynamic features of stock data. Based on the manipulated stocks, affidavits provided by the Securities and Exchange Board (SEBI) of India, a daily trading dataset is created by scraping the Bombay Stock Exchange (BSE) website. The system is capable of identifying three types of manipulation scenarios. The proposed hybrid system is compared to various supervised algorithms, and various ensemble models and the system outperforms all with an accuracy of 96.06%.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 47-79
Issue: 1/2
Volume: 26
Year: 2022
Keywords: manipulation detection; hybrid neural networks; ensemble learning; recurrent neural networks; RNNs; fraud detection; long short-term memory; LSTM; bidirectional long short-term memory; Bi-LSTM; stacked generalisation; artificial neural networks; ANNs; feature engineering.
File-URL: http://www.inderscience.com/link.php?id=121864
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:1/2:p:47-79

Template-Type: ReDIF-Article 1.0
Author-Name: Apurva Daman Katre
Author-X-Name-First: Apurva Daman
Author-X-Name-Last: Katre
Author-Name: T.C. Thanuja
Author-X-Name-First: T.C.
Author-X-Name-Last: Thanuja
Title: Joint optimisation techniques for trade-off aware spectrum sensing in cognitive radio network
Abstract:
Cognitive radio (CR) network is considered a promising domain to enhance spectrum efficiency to access underutilised frequency bands. However, due to the influence of channel fading and shadowing, accuracy in primary user (PU) detection by CR gets hampered. This paper designs a joint optimisation technique for spectrum sensing in CR network to optimise energy, delay, and throughput with increased sensing accuracy. Initially, simple energy detection is exhibited for sensing the presence of PU in band. Further, the algorithm is developed to achieve an energy-throughput trade-off, and delay-throughput trade-off. Hence, the optimisation algorithm for detecting energy, reducing delay, and enhancing throughput are developed to optimise complete sensing performance. Furthermore, the joint optimisation model assists in acquiring trade-offs amongst energy, delay, and throughput. The assessment of the technique is performed using delay, energy, and throughput. Moreover, the software-defined radio (SDR) configuration is performed for validating the result.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 1-39
Issue: 1
Volume: 27
Year: 2022
Keywords: cognitive radio network; spectrum sensing; energy; throughput; delay.
File-URL: http://www.inderscience.com/link.php?id=125997
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:27:y:2022:i:1:p:1-39

Template-Type: ReDIF-Article 1.0
Author-Name: Yan Feng
Author-X-Name-First: Yan
Author-X-Name-Last: Feng
Author-Name: Xingjian Zhou
Author-X-Name-First: Xingjian
Author-X-Name-Last: Zhou
Author-Name: Lihua Cai
Author-X-Name-First: Lihua
Author-X-Name-Last: Cai
Author-Name: Jinshan Dai
Author-X-Name-First: Jinshan
Author-X-Name-Last: Dai
Title: Research on digital logistics parks' horizontal cooperation with Cloud platform: from the perspective of tripartite evolutionary game
Abstract:
To meet the massive and emergent logistics demand, learning from Europe and the USA, a cooperation mechanism can form a gathered and scaled logistics park network. Based on the current practice in China, the logistics Cloud platform makes the cooperation from a horizontal perspective possible. A tripartite evolutionary game model consisting of one logistics Cloud platform and two digital logistics parks is proposed. The platform has strategy {compensating, no compensating}, and the parks have strategy {sharing, no sharing}. The revenue function of each party is constructed, applying dynamic replication function based on stag hunt game; all equilibrium points are found. With Jacobi matrix, two asymptotically stable strategies are formed. The study shows that the three game players either choose sharing/compensating or no sharing/no compensating strategy. The strategy is affected by the sharing/compensating probability, the compensation and opportunity cost, and the order loss. The managerial insights are also discussed.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 40-60
Issue: 1
Volume: 27
Year: 2022
Keywords: digital logistics parks; logistics Cloud platform; resource sharing; horizontal cooperation; evolutionary game.
File-URL: http://www.inderscience.com/link.php?id=125998
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:27:y:2022:i:1:p:40-60

Template-Type: ReDIF-Article 1.0
Author-Name: Lewei Hu
Author-X-Name-First: Lewei
Author-X-Name-Last: Hu
Author-Name: Jing Zhao
Author-X-Name-First: Jing
Author-X-Name-Last: Zhao
Author-Name: Yi Jiang
Author-X-Name-First: Yi
Author-X-Name-Last: Jiang
Title: E-commerce platform resources, sequence of digital strategic actions and competitive advantage: an empirical study from online tourism industry
Abstract:
This study examines the impact of the sequence of digital strategic actions initiated by e-commerce platform on competitive advantage in competitive interaction (DSAs). Based on the competitive repertoire theory, the configurational approach is used to analyse the secondary data of Chinese online tourism industry, the research finds out the configurations of DSAs orchestrated by digital technologies, partnership resources and competitor responses. Secondly, dynamic characteristics (including complexity and unpredictability) of DSAs sequence are calculated. Thirdly, panel regression has been applied to explore the relationship between the unpredictability and complexity of DSAs sequence and competitive performance in the competitive interaction, and the inverted U-shaped relationship between them is found. Finally, discussion of the implications for theory and practice is presented. In a nutshell, this study aims to help managers formulate and initiate sequences of competitive actions more effectively in the digital environment.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 61-83
Issue: 1
Volume: 27
Year: 2022
Keywords: digital strategic actions; digital technology; sequences of digital strategic actions; complexity; unpredictability; competitive repertoire.
File-URL: http://www.inderscience.com/link.php?id=125999
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:27:y:2022:i:1:p:61-83

Template-Type: ReDIF-Article 1.0
Author-Name: Zhao Du
Author-X-Name-First: Zhao
Author-X-Name-Last: Du
Author-Name: Jun Liu
Author-X-Name-First: Jun
Author-X-Name-Last: Liu
Author-Name: Fang Wang
Author-X-Name-First: Fang
Author-X-Name-Last: Wang
Title: Augmented reality in retailing: a systematic review with bibliometric analysis
Abstract:
The emergence and proliferation of augmented reality (AR) technology in retailing has revolutionised consumer shopping and service experience. A body of research on AR in business applications, particularly for retailing, is quickly developing. This research shed light on the current status of the scholarly works on AR in retailing by conducting a systematic literature review using bibliometric analysis and thematic analysis. Specifically, this research examines 51 peer-reviewed journal articles using bibliometric analysis. It provides a detailed view of the literature, including research trends, publication venues, and authorships. Moreover, it classifies and reviews three major themes and summarises the articles in each theme. Finally, this research identifies and discusses the possible directions for future research.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 84-102
Issue: 1
Volume: 27
Year: 2022
Keywords: augmented reality; retailing; systematic review; bibliometric analysis; adoption; purchase intention; product presentation; customer experience; design feature; brand attitude; market intelligence.
File-URL: http://www.inderscience.com/link.php?id=126001
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:27:y:2022:i:1:p:84-102

Template-Type: ReDIF-Article 1.0
Author-Name: Safae Berrichi
Author-X-Name-First: Safae
Author-X-Name-Last: Berrichi
Author-Name: Azzeddine Mazroui
Author-X-Name-First: Azzeddine
Author-X-Name-Last: Mazroui
Title: A word alignment study to improve the reliability of the statistical and neural translation system
Abstract:
Word alignment is an essential task for numerous natural language processing applications, including machine translation. The performance of the statistical machine translation systems is directly impacted by the performance of their alignment modules. However, such alignment models perform worse and induce low machine translation performance when translating morphological rich or low resource languages. The first objective of this paper is to examine the impact of incorporating some morphosyntactic features on the statistical alignment models and on the associated translation systems for the (Arabic, English) language pair, and to identify which of these features is most suitable. Although the neural machine translation system does not directly include a concept of word alignment, we propose, in the second part of this work, a method of adjusting the attention mechanism of these systems by the statistical alignments. Experimental results show that the proposed approaches significantly improve the alignment and the translation performances.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 104-124
Issue: 1/2
Volume: 26
Year: 2022
Keywords: morphosyntactic representation; statistical word alignment; attention mechanism; statistical translation; neural translation; Arabic language.
File-URL: http://www.inderscience.com/link.php?id=121915
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:1/2:p:104-124

Template-Type: ReDIF-Article 1.0
Author-Name: Hanene Mennour
Author-X-Name-First: Hanene
Author-X-Name-Last: Mennour
Author-Name: Sihem Mostefai
Author-X-Name-First: Sihem
Author-X-Name-Last: Mostefai
Title: Deep learning-based distributed denial-of-service detection
Abstract:
The nuisance of distributed denial-of-service (DDoS) attacks has extended unremittingly nowadays. Thus, guaranteeing system availability in this open-ended pandemic is a crucial task. In this work, we propose three different deep learning strategies as a network anomaly-based intrusion detection system (N-IDS) for a DDoS multi-classification task. We built a deep convolutional neural network (CNN), a stacked long short-term memory (S-LSTM) neural network which is a distinct artificial recurrent neural network (RNN), the third model is a hybridisation between CNN and LSTM. Then, we evaluated them on three up to date flow-based datasets: CICIDS2017, CICDDoS2019 and BoT-IoT benchmarks. The outcomes demonstrate that hybrid CNN-LSTM outperforms the existing state-of-the-art schemes in almost all the validation metrics.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 80-103
Issue: 1/2
Volume: 26
Year: 2022
Keywords: deep learning; intrusion detection system; IDS; network intrusion detection system; NIDS; anomaly-based; distributed denial-of-service; DDoS; multi-classification; convolutional neural network; CNN; long short-term memory; LSTM; flow-based; CICDDoS2019.
File-URL: http://www.inderscience.com/link.php?id=121921
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:1/2:p:80-103

Template-Type: ReDIF-Article 1.0
Author-Name: Farooq Ali
Author-X-Name-First: Farooq
Author-X-Name-Last: Ali
Author-Name: Harri Haapasalo
Author-X-Name-First: Harri
Author-X-Name-Last: Haapasalo
Author-Name: Kari-Pekka Tampio
Author-X-Name-First: Kari-Pekka
Author-X-Name-Last: Tampio
Author-Name: Henriikka Haapasalo
Author-X-Name-First: Henriikka
Author-X-Name-Last: Haapasalo
Title: Analysing the challenges in stakeholder relationship management in the healthcare process: a social network perspective
Abstract:
We investigate stakeholder relationship management and identify challenges that impact relationships at the healthcare process level using the inductive research approach. We adopt an inductive approach and grounded theory method since there is a need for detailed descriptions on stakeholder network, especially on relationship management. The emergent grounded theoretical model explains the challenges that impact stakeholder relationship management, i.e., gaps in the healthcare network, challenges in articulating a healthcare vision, triggers of challenges, contextual challenges, healthcare landscape, challenges in trust-building, and collaboration. Additionally, our findings show how the network structure and stakeholders' position in the network, based on their interactions' patterns, influence stakeholder relationship management. The grounded theory that emerged from our study confirms several themes and their interrelationships, which constitute our main contribution.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 125-156
Issue: 1/2
Volume: 26
Year: 2022
Keywords: stakeholder relationship management; healthcare process; social network; stakeholder network; network structure; healthcare network; healthcare management; grounded theory; stakeholder identification; stakeholder mapping.
File-URL: http://www.inderscience.com/link.php?id=121934
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:1/2:p:125-156

Template-Type: ReDIF-Article 1.0
Author-Name: Suya Hu
Author-X-Name-First: Suya
Author-X-Name-Last: Hu
Author-Name: Di Xu
Author-X-Name-First: Di
Author-X-Name-Last: Xu
Author-Name: Yan Li
Author-X-Name-First: Yan
Author-X-Name-Last: Li
Title: Leveraging linguistic signalling to prompt feedback in open innovation communities
Abstract:
The rise of open innovation communities (OICs) has enabled organisations to gain ideas from the outside. Although current studies mainly focus on idea generation behaviours among participants, little attention has been paid to the subsequent interactive feedback, which is equally important for the success of running OICs. Drawing on signalling theory, we empirically examine how to leverage signals expressed in idea descriptions to influence feedback from two key parties: the moderator and peers. Two linguistic features, i.e., affective signalling (linguistic style matching, negative emotion, and impoliteness) and informative signalling (post length and quality) are proposed. Analysing data collected from the Huawei community, we find that feedback from the moderator is indeed influenced by both affective and informative signalling. Furthermore, only negative emotion is positively associated with feedback from peers, while the effects of other signals show different trends. This study offers practical insights into how to maintain the viability of OICs.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 249-267
Issue: 4
Volume: 26
Year: 2022
Keywords: feedback; signalling theory; ideas; open innovation communities; OICs.
File-URL: http://www.inderscience.com/link.php?id=124764
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:4:p:249-267

Template-Type: ReDIF-Article 1.0
Author-Name: Minghua He
Author-X-Name-First: Minghua
Author-X-Name-Last: He
Title: Understanding residents' continued usage intention of community sharing platforms in smart communities in a post-COVID era: evidence from China
Abstract:
A community sharing platform has demonstrated its significant role in prevention and control of COVID-19 pandemic in communities throughout China. Despite its increasing popularity, the widespread adoption and continued usage intention of smart community sharing platforms by the residents is still far underexplored. Thus, this study applied the technology acceptance model (TAM) as the research framework to empirically investigate the factors influencing residents' continued intention to use community sharing platforms in the post-COVID era. Empirical results show that perceived ease of use, perceived usefulness and sharing attitude significantly impact residents' continued intention to use smart community sharing platforms and that residents' education level significantly moderates the relationships between the three kinds of antecedents and continued usage intention. This study contributes to the literature in the field of smart communities and provides practical implications for governments and platform operators to achieve sustainable development of community sharing platforms.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 268-290
Issue: 4
Volume: 26
Year: 2022
Keywords: community sharing platform; smart communities; continued usage intention; technology acceptance model; TAM; China.
File-URL: http://www.inderscience.com/link.php?id=124765
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:4:p:268-290

Template-Type: ReDIF-Article 1.0
Author-Name: Azim Naz M.
Author-X-Name-First: Azim Naz
Author-X-Name-Last: M.
Author-Name: R. Sarath
Author-X-Name-First: R.
Author-X-Name-Last: Sarath
Title: Optimisation assisted CNN framework for bearing fault diagnosis
Abstract:
Nowadays, intellectual fault diagnosis mechanism with DL schemes was extensively deployed in production firms to develop the effectiveness of fault diagnosis. The rolling bearings connect the support and rotor and are considered as a critical element in rotating equipments. Nevertheless, the working state of bearing varies based on composite operation demand that may drastically corrupt the performances of the intellectual fault diagnosis technique. Thereby, this scheme develops novel fault diagnosis schemes that included the two most important stages like 'feature extraction' and 'classification'. Initially, the features namely, 'empirical wavelet transform', 'empirical mode decomposition' and 'wavelet transform' are extracted. Subsequent to this, the derived features are classified via 'optimised convolutional neural network' is employed. Further, to get better accuracy using adopted model, the weights of CNN is tuned via self-adaptive moth-flame optimisation. Eventually, the primacy of the offered scheme is proven regarding varied measures. Eventually, the proposed technique has obtained a superior value of 0.922, and it is 1.62%, 1.92%, 50.76%, and 57.34%, superior to existing MFO, FF, SVM and RF models for dataset 1.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 291-308
Issue: 4
Volume: 26
Year: 2022
Keywords: fault diagnosis; EWT features; EMD features; CNN; SA-MFA algorithm.
File-URL: http://www.inderscience.com/link.php?id=124767
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:4:p:291-308

Template-Type: ReDIF-Article 1.0
Author-Name: M. Padmapriya
Author-X-Name-First: M.
Author-X-Name-Last: Padmapriya
Author-Name: S. Pasupathy
Author-X-Name-First: S.
Author-X-Name-Last: Pasupathy
Author-Name: R. Sumathi
Author-X-Name-First: R.
Author-X-Name-Last: Sumathi
Author-Name: V. Punitha
Author-X-Name-First: V.
Author-X-Name-Last: Punitha
Title: A deep learning model framework for diabetic retinopathy detection
Abstract:
Diabetic retinopathy (DR) is the typical diabetic eye issue and a main reason of blindness around the world. As per the International Diabetes Federation (IDF), the rates of diabetes would rise to 552 million by 2034. Breakthroughs in computer science techniques inclusive of artificial intelligence (AI) and deep learning (DL) have multiplied opportunities for early detection of DR. This indicates that the likelihood of a patient's healing will improve, and the risk of eyesight loss could be minimised in due course. A deep learning model (ResNet) for medical DR detection was examined in this article. The dataset of Asia Pacific Tele-Ophthalmology Society (APTOS) 2019 was used to train and test the DL model. To demonstrate the vitality of the chosen ResNet model, performance measures and testing accuracy like recall, precision, and F1 score were determined. The modified ResNet model attained a testing accuracy of around 84% even with only a few dataset images. Also, training time and computational complexity were reduced with this simpler model.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 107-124
Issue: 2
Volume: 27
Year: 2022
Keywords: diabetic retinopathy; convolutional neural network; CNN; machine learning; deep learning; ResNet model.
File-URL: http://www.inderscience.com/link.php?id=127584
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:27:y:2022:i:2:p:107-124

Template-Type: ReDIF-Article 1.0
Author-Name: Haixiang He
Author-X-Name-First: Haixiang
Author-X-Name-Last: He
Title: Research on community-based group communication behaviours in convergence media
Abstract:
The emergence of the internet has led to the convergence of traditional media, greatly improving the speed of information dissemination but also enabling the rapid spread of undesirable information. To avoid the rapid spread of undesirable information that affects social stability, it is necessary to analyse the community-based group communication behaviour in convergence media. This paper briefly introduces convergence media and the community-based group communication behaviour in convergence media and uses structural equation modelling to analyse the group communication behaviour. The results showed that the stimulation degree of stimulating events, individual characteristics, and group structure was positively correlated with the implementation intention; contextual factors were positively correlated with stimulating events, individual characteristics and group structure.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 309-318
Issue: 4
Volume: 26
Year: 2022
Keywords: community-based; convergence media; group communication behaviour; structural equation model.
File-URL: http://www.inderscience.com/link.php?id=124775
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:4:p:309-318

Template-Type: ReDIF-Article 1.0
Author-Name: Guangqian Peng
Author-X-Name-First: Guangqian
Author-X-Name-Last: Peng
Author-Name: Yan Zhang
Author-X-Name-First: Yan
Author-X-Name-Last: Zhang
Author-Name: Ping Gao
Author-X-Name-First: Ping
Author-X-Name-Last: Gao
Author-Name: Yiming Yuan
Author-X-Name-First: Yiming
Author-X-Name-Last: Yuan
Author-Name: Junfeng Yin
Author-X-Name-First: Junfeng
Author-X-Name-Last: Yin
Title: The impact of big data capability: a perspective of supply chain and innovation capabilities
Abstract:
The study on big data capability was initiated just recently. The impact of big data capability on companies, such as on companies' other capabilities, is still unclear. Grounded on dynamic capabilities theory, this study proposed a model and tested the impact of big data capability on supply chain dynamic capability and dynamic innovation capability. The research objects are high-tech listed companies in China. By PLS path modelling, the major findings are: 1) big data capability showed positive impact on supply chain dynamic capability; 2) however, unexpectedly, big data capability was found showing negative impact on dynamic innovation capability. In our opinion, the potential reason is that big data application is just initiated, so may lead to certain disorder in the companies. Based on this finding, we call for attention to big data paradox; 3) further, supply chain dynamic capability showed positive impact on dynamic innovation capability; 4) possibly owing to the mediating and moderating effects of supply chain dynamic capability, the total effect of big data capability on dynamic innovation capability is positive and significant. Managerial applications and limitations are generalised at the end.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 319-331
Issue: 4
Volume: 26
Year: 2022
Keywords: big data capability; dynamic capability; supply chain dynamic capability; dynamic innovation capability; big data paradox.
File-URL: http://www.inderscience.com/link.php?id=124781
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:4:p:319-331

Template-Type: ReDIF-Article 1.0
Author-Name: Rakesh Kumar Pattanaik
Author-X-Name-First: Rakesh Kumar
Author-X-Name-Last: Pattanaik
Author-Name: Rinky Dwivedi
Author-X-Name-First: Rinky
Author-X-Name-Last: Dwivedi
Author-Name: Mihir Narayan Mohanty
Author-X-Name-First: Mihir Narayan
Author-X-Name-Last: Mohanty
Title: Application of nonlinear system identification for EEG modelling using VMD-based deep random vector functional link network
Abstract:
In this paper, the EEG signal is considered for the development of the model. As the signal is nonlinear and non-stationary, the model is designed accordingly which is similar to nonlinear dynamic system identification. Initially, the signal is decomposed by a robust variational mode decomposition method for which the basic noise components are eliminated. Later, a kurtosis index method is applied to choose the best band-limited intrinsic mode functions (BLIMFs) based on their clean coefficient the model is developed using a random vector functional link neural network (RVFLN) for identification. The use of deep RVFLN provides better results as compared to simple RVFLN as explained in the result section. For verification of the system's robustness, three different epileptic signals known as pre-ictal, inter-ictal and ictal are experienced in this piece of work.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 125-142
Issue: 2
Volume: 27
Year: 2022
Keywords: variational mode decomposition; linear time-invariant; random vector functional link network; RVFLN; nonlinear system identification; electroencephalogram; EEG.
File-URL: http://www.inderscience.com/link.php?id=127601
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:27:y:2022:i:2:p:125-142

Template-Type: ReDIF-Article 1.0
Author-Name: Indresh Kumar Gupta
Author-X-Name-First: Indresh Kumar
Author-X-Name-Last: Gupta
Author-Name: Abha Choubey
Author-X-Name-First: Abha
Author-X-Name-Last: Choubey
Author-Name: Siddhartha Choubey
Author-X-Name-First: Siddhartha
Author-X-Name-Last: Choubey
Title: Salp swarm optimisation with deep transfer learning enabled retinal fundus image classification model
Abstract:
Automated screening and diagnostic process in the healthcare sector improves services, reduces cost and labour. With the developments of machine learning (ML) and deep learning (DL) models, intelligent disease diagnosis models can be designed. Retinal fundus image classification using DL models becomes essential for the identification and classification of distinct retinal diseases. This article develops a salp swarm optimisation with deep transfer learning enabled retinal fundus image classification (SSODTL-RFIC) model. The proposed SSODTL-RFIC model examines the retinal fundus image for the existence of diseases. In addition, a median filtering (MF) approach is employed for the noise removal process and graph cut (GC) segmentation is applied. Besides, MobileNetv1 feature extractor is involved to produce feature vectors. Finally, SSO with cascade forward neural network (CFNN) model is applied for recognition and classification process. A widespread experimentation process is performed on benchmark datasets to examine the enhanced performance of the SSODTL-RFIC model, an extensive comparative examination pointed out the supremacy of the SSODTL-RFIC model over the recent approaches with maximum accuracy of 98.71% and 99.12% on the test ARIA and STARE datasets respectively.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 163-180
Issue: 2
Volume: 27
Year: 2022
Keywords: retinal fundus images; image classification; machine learning; deep learning; salp swarm algorithm; cascade forward neural network; CFNN.
File-URL: http://www.inderscience.com/link.php?id=127605
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:27:y:2022:i:2:p:163-180

Template-Type: ReDIF-Article 1.0
Author-Name: R. Raja
Author-X-Name-First: R.
Author-X-Name-Last: Raja
Author-Name: B. Ashok
Author-X-Name-First: B.
Author-X-Name-Last: Ashok
Title: Evolutionary optimisation with outlier detection-based deep learning model for biomedical data classification
Abstract:
In recent times, large amount of medical data is being generated by various sources such as test reports, medications, etc. Due to the recent advances of machine learning (ML) and deep learning (DL) models, medical data classification (MDC) remains a crucial process in the healthcare sector. This study introduces a new hyperparameter tuned convolutional neural network-recurrent neural network (HPT-CNN-RNN) model for medical data classification. The proposed HPT-CNN-RNN model includes pre-processing step to transform the actual healthcare data into useful format. Besides, SVM-SMOTE approach was executed to handle the class imbalance problems. In addition, outlier detection process is performed using extreme gradient boosting (XGBoost) model. Moreover, bacterial foraging optimisation algorithm (BFOA) with CNNRNN model is employed to categorise medical data. Furthermore, the BFOA is utilised to optimally choose the hyperparameter values of the CNNRNN model. The experimental outcomes designated the better performance of the HPT-CNN-RNN model over the other methods.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 143-162
Issue: 2
Volume: 27
Year: 2022
Keywords: classification; medical data; data mining; outlier detection; class imbalance; deep learning; parameter tuning.
File-URL: http://www.inderscience.com/link.php?id=127606
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:27:y:2022:i:2:p:143-162

Template-Type: ReDIF-Article 1.0
Author-Name: Nursakirah Ab Rahman Muton
Author-X-Name-First: Nursakirah Ab Rahman
Author-X-Name-Last: Muton
Author-Name: Norhayati Zakaria
Author-X-Name-First: Norhayati
Author-X-Name-Last: Zakaria
Author-Name: Asmat-Nizam Abdul-Talib
Author-X-Name-First: Asmat-Nizam
Author-X-Name-Last: Abdul-Talib
Author-Name: Shafiz Affendi Mohd Yusof
Author-X-Name-First: Shafiz Affendi Mohd
Author-X-Name-Last: Yusof
Title: Should I accommodate you? Cross-cultural code-switching behaviours of global virtual team members during swift trust formation
Abstract:
This conceptual paper explores the process of cross-cultural code-switching (C<SUP align=right><SMALL>3</SMALL></SUP>S) between high-context (HC) and low-context (LC) global virtual team members during the knowledge-sharing and social network exchanges. We will introduce a cross-cultural code-switching framework in a virtual setting and develop propositions to explain how GVT members attempt to switch their communicative behaviour based on two theoretical lenses: Giles communication accommodation theory (1973) and Hall high-context and low-context theory (1976). This paper offers several propositions to illuminate the process of code-switching behaviours among GVT members during the socialisation process and explores how these behaviours help develop swift trust. It considers whether developing swift trust is possible and, if so, how. We will provide future research directions in our concluding remarks.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 157-171
Issue: 3
Volume: 26
Year: 2022
Keywords: cross-cultural code-switching behaviour; knowledge sharing; high-context and low-context cultures; communication accommodation theory; CAT; global virtual teams; GVTs; communication styles; communicative behaviour; Malaysia.
File-URL: http://www.inderscience.com/link.php?id=122847
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:3:p:157-171

Template-Type: ReDIF-Article 1.0
Author-Name: Aung Pyae
Author-X-Name-First: Aung
Author-X-Name-Last: Pyae
Title: A usability evaluation of the Google Home with non-native English speakers using the system usability scale
Abstract:
Advancements in multidisciplinary research have made voice user interfaces (VUIs) become a reality in both research and commercialisation. Although the existing research has indicated that VUIs are useful in people's daily lives (e.g., personal assistant), there is limited study on non-native English-speaking users' experiences in using commercial VUIs. Hence, in this study, the Google Home Smart Speaker was evaluated with 34 undergraduate students, who use English as a second language, to investigate its usability and user experiences. The SUS, PSSUQ, heuristics questionnaires, and interview questions were used to evaluate the Google Home's usability. The findings report that the Google Home is user-friendly, usable, and useful for non-native English-speaking users. Considering unsolved usability issues found in this study, some usability guidelines are recommended for the design and implementation of future VUIs. The findings also suggest that the SUS is suitable for the assessment of non-native English speakers' use of VUIs.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 172-194
Issue: 3
Volume: 26
Year: 2022
Keywords: smart speaker; usability; human-computer interaction; voice user interface; VUI; system usability scale; SUS; Post-Study System Usability Questionnaire; PSSUQ; heuristics.
File-URL: http://www.inderscience.com/link.php?id=122849
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:3:p:172-194

Template-Type: ReDIF-Article 1.0
Author-Name: Tian Wang
Author-X-Name-First: Tian
Author-X-Name-Last: Wang
Author-Name: Ding Zhang
Author-X-Name-First: Ding
Author-X-Name-Last: Zhang
Title: Trade-off between two advertising strategies: coverage or penetration
Abstract:
There are two different basic advertising strategies, namely, enlarging the market coverage and improving the market penetration. Efforts in the first (coverage) strategy can be seen as handing out leaflets, advertising board and huge-crowd acquisition. Efforts in the second (penetration) strategy can be seen as improving product quality, service environment and positive word-of-mouth. Which one is more efficient, coverage or penetration? How do firm trade-off between the two advertising strategies? By establishing two-stage models, this paper explores the optimal advertising levels for the two strategies, respectively. After that, this paper compares the optimal profits under the two strategies in various market settings and finds the more efficient advertising strategy. Management insights are generated for decision-makings of firm managers.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 195-211
Issue: 3
Volume: 26
Year: 2022
Keywords: advertising; market coverage; market penetration.
File-URL: http://www.inderscience.com/link.php?id=122853
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:3:p:195-211

Template-Type: ReDIF-Article 1.0
Author-Name: Suya Hu
Author-X-Name-First: Suya
Author-X-Name-Last: Hu
Author-Name: Di Xu
Author-X-Name-First: Di
Author-X-Name-Last: Xu
Author-Name: Alan Wang
Author-X-Name-First: Alan
Author-X-Name-Last: Wang
Title: Idea response and adoption in open innovation communities: the signalling role of linguistic style
Abstract:
Open innovation communities have become a new trend for organisations to gain external ideas and foster user innovation. However, mass user generated content is making idea selection a tricky and time-consuming work. From the perspective of linguistic styles, this article explores the effects of writing style cues in the content of ideas on idea response and adoption. Our research model is validated through logistic regression on a secondary dataset of 1,579 ideas collected from the Fantasy Westward Journey Online forum. The results demonstrate that a member's use of self-interest oriented, cognitive oriented and future oriented writing styles has a positive effect on idea response; negative emotionality and cognitive oriented writing styles signal more possibility of idea adoption. We highlight both theoretical implications and managerial applications in innovation management domains.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 212-230
Issue: 3
Volume: 26
Year: 2022
Keywords: open innovation community; user innovation; linguistic style; idea response; idea adoption.
File-URL: http://www.inderscience.com/link.php?id=122856
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:3:p:212-230

Template-Type: ReDIF-Article 1.0
Author-Name: Sunaina Arora
Author-X-Name-First: Sunaina
Author-X-Name-Last: Arora
Author-Name: Neeraj Kumari
Author-X-Name-First: Neeraj
Author-X-Name-Last: Kumari
Title: Imagining benefits and challenges for future hybrid workplace to enable reentry for women on career break
Abstract:
COVID-19 has shifted everyone to remote work. The paper discusses how employees have overcome various challenges to make most of the benefits of remote work. The benefits of remote work are flexible work arrangements, ease of working, access to global opportunities and positive impact on diversity hiring. The challenges of remote work are access to technology, tackling virtual distance and managing productivity. Exploratory research was conducted with a sample size of 93. Data was analysed using SPSS. The sample comprised of professionals who were working from home during the COVID-19 pandemic. The study verified the hypothesis using Spearman rank order correlation. The respondents are ready to overcome the challenges of remote work because of the benefits which remote work provides. Data verifies that hybrid workplace would enable to open doors for women on career break to reenter workforce.
Journal: Int. J. of Networking and Virtual Organisations
Pages: 231-248
Issue: 3
Volume: 26
Year: 2022
Keywords: remote work; hybrid workplace; women on career break; work from home.
File-URL: http://www.inderscience.com/link.php?id=122857
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:3:p:231-248

Template-Type: ReDIF-Article 1.0
Author-Name: Zohra Amekraz
Author-X-Name-First: Zohra
Author-X-Name-Last: Amekraz
Author-Name: Moulay Youssef Hadi
Author-X-Name-First: Moulay Youssef
Author-X-Name-Last: Hadi
Title: A cluster workload forecasting strategy using a higher order statistics based ARMA model for IaaS cloud services
Abstract:
With cloud services becoming more popular among internet users, cloud providers are facing a challenge in allocating resources according to users' demand instantly due to the delay caused by the virtual machines' start up time. This problem can be solved using proactive allocation techniques that predict the workload in advance and make scaling decisions ahead of time. In this paper, we present an adaptive workload prediction method based on higher order statistics (HOS) and autoregressive moving average (ARMA) model. We use HOS to make a Gaussianity checking test of the cloud workload and decide the suitable identification method of the ARMA model to be used for forecasting. We evaluate our proposal with two real traces extracted from cluster workloads. The results show that the proposed method has an average of 34% higher accuracy than the baseline ARMA model and presents a low forecasting overhead (< 2 s).
Journal: Int. J. of Networking and Virtual Organisations
Pages: 3-22
Issue: 1/2
Volume: 26
Year: 2022
Keywords: IaaS cloud services; workload prediction; cluster workload; autoregressive moving average; ARMA; higher order statistics; HOS.
File-URL: http://www.inderscience.com/link.php?id=121844
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:1/2:p:3-22

Template-Type: ReDIF-Article 1.0
Author-Name: Zohra Amekraz
Author-X-Name-First: Zohra
Author-X-Name-Last: Amekraz
Author-Name: Moulay Youssef Hadi
Author-X-Name-First: Moulay Youssef
Author-X-Name-Last: Hadi
Title: Cloud spot price prediction approach using adaptive neural fuzzy inference system with chaos theory
Abstract:
The dynamic pricing of cloud computing is a major challenge for cloud users all over the world. This challenge was first addressed by Amazon under the name of Amazon spot instance market. Cloud users can bid for a spot instance using this market and obtain the requested spot if their bids exceed a dynamically changing spot price. Amazon publicises the spot price but does not reveal how it is determined. In this paper, we perform chaotic time series analysis over the spot price trace. We also develop a chaos based adaptive neural fuzzy inference system (ANFIS) model based on phase-space vectors obtained during the phase of chaotic analysis. Next, we study the effect of chaos existence on the prediction accuracy of the spot price by comparing the proposed chaos-ANFIS model with the baseline ANFIS model (non-chaotic approach). Evaluation results show that the proposed chaos-ANFIS model yields better predictions of spot price compared to the baseline ANFIS model in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE).
Journal: Int. J. of Networking and Virtual Organisations
Pages: 23-46
Issue: 1/2
Volume: 26
Year: 2022
Keywords: dynamic pricing; cloud computing; spot instance; spot price; chaotic time series analysis; ANFIS.
File-URL: http://www.inderscience.com/link.php?id=121845
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijnvor:v:26:y:2022:i:1/2:p:23-46