Multi-dataset hyper-cnn for hyperspectral image segmentation of remote sensing images
- Liu, Li, Awwad, Emad, Ali, Yasser, Al-Razgan, Muna, Maarouf, Ali, Abualigah, Laith, Hoshyar, Azadeh
- Authors: Liu, Li , Awwad, Emad , Ali, Yasser , Al-Razgan, Muna , Maarouf, Ali , Abualigah, Laith , Hoshyar, Azadeh
- Date: 2023
- Type: Text , Journal article
- Relation: Processes Vol. 11, no. 2 (2023), p.
- Full Text:
- Reviewed:
- Description: This research paper presents novel condensed CNN architecture for the recognition of multispectral images, which has been developed to address the lack of attention paid to neural network designs for multispectral and hyperspectral photography in comparison to RGB photographs. The proposed architecture is able to recognize 10-band multispectral images and has fewer parameters than popular deep designs, such as ResNet and DenseNet, thanks to recent advancements in more efficient smaller CNNs. The proposed architecture is trained from scratch, and it outperforms a comparable network that was trained on RGB images in terms of accuracy and efficiency. The study also demonstrates the use of a Bayesian variant of CNN architecture to show that a network able to process multispectral information greatly reduces the uncertainty associated with class predictions in comparison to standard RGB images. The results of the study are demonstrated by comparing the accuracy of the network’s predictions to the images. © 2023 by the authors.
- Authors: Liu, Li , Awwad, Emad , Ali, Yasser , Al-Razgan, Muna , Maarouf, Ali , Abualigah, Laith , Hoshyar, Azadeh
- Date: 2023
- Type: Text , Journal article
- Relation: Processes Vol. 11, no. 2 (2023), p.
- Full Text:
- Reviewed:
- Description: This research paper presents novel condensed CNN architecture for the recognition of multispectral images, which has been developed to address the lack of attention paid to neural network designs for multispectral and hyperspectral photography in comparison to RGB photographs. The proposed architecture is able to recognize 10-band multispectral images and has fewer parameters than popular deep designs, such as ResNet and DenseNet, thanks to recent advancements in more efficient smaller CNNs. The proposed architecture is trained from scratch, and it outperforms a comparable network that was trained on RGB images in terms of accuracy and efficiency. The study also demonstrates the use of a Bayesian variant of CNN architecture to show that a network able to process multispectral information greatly reduces the uncertainty associated with class predictions in comparison to standard RGB images. The results of the study are demonstrated by comparing the accuracy of the network’s predictions to the images. © 2023 by the authors.
Impact of workplace guanxi on knowledge sharing and innovative work behaviour : a study of academic staff of Chinese local universities in Guangdong Province
- Liu, Li
- Authors: Liu, Li
- Date: 2020
- Type: Text , Thesis , PhD
- Full Text:
- Description: This thesis aims to investigate the impact of workplace guanxi upon knowledge sharing and innovative work behaviour. Knowledge sharing and innovative work behaviour are two behavioural variables which have been linked to various positive individual and organisational outcomes. Against the changing landscape of Chinese higher education, the two behaviours are particularly important for the success of Chinese academic staff and the local universities where they work. Extant literature has demonstrated that workplace interpersonal relationships such as leader-member exchange and team-member exchange are positively associated with individual’s work behaviours, such as knowledge sharing and innovative work behaviour. However, there is a scant literature on the impact of workplace guanxi upon the two workplace behaviours. Using conservation of resource theory and social exchange theory, this research conceptualised a structural model to study the impact of workplace guanxi upon knowledge sharing and innovative work behaviour. A positivist approach with cross-sectional design and structural equation modelling was adopted to test the conceptualised model. Data were extracted from 479 academic staff of seven local universities in Guangdong Province of China, through selfreport questionnaire. A positive relationship was found between coworker guanxi and knowledge sharing. In contrast, no relationship was found between supervisor-subordinate guanxi and knowledge sharing. The relationship between coworker guanxi and knowledge sharing was fully mediated by teammember exchange and job satisfaction. In terms of innovative work behaviour, both supervisorsubordinate guanxi and coworker guanxi displayed a positive relationship with innovative work behaviour. Coworker guanxi showed a stronger relationship with innovative work behaviour than supervisor-subordinate guanxi did. The relationship between supervisorsubordinate guanxi and innovative work behaviour was direct. The relationship between coworker guanxi and innovative work behaviour was indirect, with full mediation of teammember exchange, job satisfaction and knowledge sharing. This thesis contributes to the literature on explaining the role of workplace guanxi, including supervisor-subordinate guanxi and coworker guanxi on knowledge sharing and innovative work behaviour. The study also demonstrates to higher education institute managers that the cultivation of academic staff’s workplace guanxi, and particularly their guanxi with peer academics, promotes academic staff’s displays of knowledge sharing and innovative work behaviour which are beneficial at both individual and organisational levels within the higher education context.
- Description: Doctor of Philosophy
- Authors: Liu, Li
- Date: 2020
- Type: Text , Thesis , PhD
- Full Text:
- Description: This thesis aims to investigate the impact of workplace guanxi upon knowledge sharing and innovative work behaviour. Knowledge sharing and innovative work behaviour are two behavioural variables which have been linked to various positive individual and organisational outcomes. Against the changing landscape of Chinese higher education, the two behaviours are particularly important for the success of Chinese academic staff and the local universities where they work. Extant literature has demonstrated that workplace interpersonal relationships such as leader-member exchange and team-member exchange are positively associated with individual’s work behaviours, such as knowledge sharing and innovative work behaviour. However, there is a scant literature on the impact of workplace guanxi upon the two workplace behaviours. Using conservation of resource theory and social exchange theory, this research conceptualised a structural model to study the impact of workplace guanxi upon knowledge sharing and innovative work behaviour. A positivist approach with cross-sectional design and structural equation modelling was adopted to test the conceptualised model. Data were extracted from 479 academic staff of seven local universities in Guangdong Province of China, through selfreport questionnaire. A positive relationship was found between coworker guanxi and knowledge sharing. In contrast, no relationship was found between supervisor-subordinate guanxi and knowledge sharing. The relationship between coworker guanxi and knowledge sharing was fully mediated by teammember exchange and job satisfaction. In terms of innovative work behaviour, both supervisorsubordinate guanxi and coworker guanxi displayed a positive relationship with innovative work behaviour. Coworker guanxi showed a stronger relationship with innovative work behaviour than supervisor-subordinate guanxi did. The relationship between supervisorsubordinate guanxi and innovative work behaviour was direct. The relationship between coworker guanxi and innovative work behaviour was indirect, with full mediation of teammember exchange, job satisfaction and knowledge sharing. This thesis contributes to the literature on explaining the role of workplace guanxi, including supervisor-subordinate guanxi and coworker guanxi on knowledge sharing and innovative work behaviour. The study also demonstrates to higher education institute managers that the cultivation of academic staff’s workplace guanxi, and particularly their guanxi with peer academics, promotes academic staff’s displays of knowledge sharing and innovative work behaviour which are beneficial at both individual and organisational levels within the higher education context.
- Description: Doctor of Philosophy
- «
- ‹
- 1
- ›
- »