Padmavati Shrivastava, K.K. Bhoyar and A.S. Zadgaonkar
The purpose of this paper is to build a classification system which mimics the perceptual ability of human vision, in gathering knowledge about the structure, content and the…
Abstract
Purpose
The purpose of this paper is to build a classification system which mimics the perceptual ability of human vision, in gathering knowledge about the structure, content and the surrounding environment of a real-world natural scene, at a quick glance accurately. This paper proposes a set of novel features to determine the gist of a given scene based on dominant color, dominant direction, openness and roughness features.
Design/methodology/approach
The classification system is designed at two different levels. At the first level, a set of low level features are extracted for each semantic feature. At the second level the extracted features are subjected to the process of feature evaluation, based on inter-class and intra-class distances. The most discriminating features are retained and used for training the support vector machine (SVM) classifier for two different data sets.
Findings
Accuracy of the proposed system has been evaluated on two data sets: the well-known Oliva-Torralba data set and the customized image data set comprising of high-resolution images of natural landscapes. The experimentation on these two data sets with the proposed novel feature set and SVM classifier has provided 92.68 percent average classification accuracy, using ten-fold cross validation approach. The set of proposed features efficiently represent visual information and are therefore capable of narrowing the semantic gap between low-level image representation and high-level human perception.
Originality/value
The method presented in this paper represents a new approach for extracting low-level features of reduced dimensionality that is able to model human perception for the task of scene classification. The methods of mapping primitive features to high-level features are intuitive to the user and are capable of reducing the semantic gap. The proposed feature evaluation technique is general and can be applied across any domain.
Details
Keywords
Harish Kumar Singla, Abhishek Shrivas and Ashu Sharma
The previous researchers have identified human capital, relational capital and structural capital as knowledge assets in knowledge-driven organizations. The current study is an…
Abstract
Purpose
The previous researchers have identified human capital, relational capital and structural capital as knowledge assets in knowledge-driven organizations. The current study is an attempt to identify and validate the knowledge assets in construction projects. The study also aims to understand the interrelation of these knowledge assets and their impact on project performance through the development of a conceptual model.
Design/methodology/approach
The study is divided into three phases. In phase I, the constructs of “knowledge assets” and “project performance” in construction projects are identified using the exploratory factor analysis. In phase II, these constructs are validated using confirmatory factor analysis. Two separate surveys are conducted for phase I and phase II, respectively. In phase III, the authors develop two conceptual models based on the literature review and two construction project cases in India. The models examine the inter-relationship of knowledge assets and measures their impact on project performance. The models are empirically tested using the responses of the second survey through a structural equation model.
Findings
The study extracts four knowledge asset constructs and one performance construct which are named human capital, structural capital, relational capital, human capital capacity building process and project performance, respectively. The study finds that both the conceptual models are statistically excellent fit. The results of the models suggest that relational capital and structural capital have a direct positive impact on project performance, whereas human capital has an indirect effect on project performance mediated through relational capital, structural capital and human capital capacity building process.
Research limitations/implications
The items for knowledge asset constructs and measurement of project performance are moderated by experts, working in construction projects in India, hence the process may contain subjective bias. Further, two construction project cases were selected by authors in the study that originate from India.
Practical implications
The study has implications for the project executors (contractors) as well as for project owners. The contractors must maintain healthy relations with all the stakeholders in a project like a client, suppliers, architects, etc. They must develop systems that are people-friendly to avoid the problems of time and cost overruns in projects. The owners must also maintain healthy relations. This can result in a win-win situation for both parties and can lead to superior project performance.
Originality/value
The study develops and empirically tests two conceptual models that explain the interrelations of knowledge assets and how it benefits the construction project performance in India. Therefore, the generalization of the results is difficult; however, the results can be replicated in projects with similar settings.
Details
Keywords
Meliha Handzic, Nermina Durmic, Adnan Kraljic and Tarik Kraljic
The purpose of this paper is to empirically investigate the relationship between project-specific intellectual capital (IC) and project success in the context of information…
Abstract
Purpose
The purpose of this paper is to empirically investigate the relationship between project-specific intellectual capital (IC) and project success in the context of information technology (IT) projects.
Design/methodology/approach
Using data collected from surveys of 603 IT professionals across a variety of projects, the authors constructed a structural (structural equation model) model in AMOS to examine the relationships between three dimensions of project-specific IC (project team, project customer and project process) and project success.
Findings
The empirical results support the proposition that IC has a positive impact on project success, and thus may be a good indicator of future projects’ performance. More importantly, the authors found out an important mediating role of a project’s structural capital (process) in exploiting its human (team) and relational (customer) capital for realising project success.
Research limitations/implications
Interpretation of current results should be considered in light of the following methodological limitations: convenient rather than systematic sampling, use of previously untested measures and prevailing European subjects.
Practical implications
These results suggest that project-based organisations need to invest heavily in their project workforce talent and then translate it into superior project practices in order to produce successful IT projects. They also need to maintain close relationships with their project customers and involve them during the entire project process.
Originality/value
The current empirical evidence extends the understanding of the role of IC in improving project success and thus helps project-based organisations create and maintain competitive advantage in emerging economies.
Details
Keywords
Mohammad Mahdi Ershadi and Abbas Seifi
This study aims to differential diagnosis of some diseases using classification methods to support effective medical treatment. For this purpose, different classification methods…
Abstract
Purpose
This study aims to differential diagnosis of some diseases using classification methods to support effective medical treatment. For this purpose, different classification methods based on data, experts’ knowledge and both are considered in some cases. Besides, feature reduction and some clustering methods are used to improve their performance.
Design/methodology/approach
First, the performances of classification methods are evaluated for differential diagnosis of different diseases. Then, experts' knowledge is utilized to modify the Bayesian networks' structures. Analyses of the results show that using experts' knowledge is more effective than other algorithms for increasing the accuracy of Bayesian network classification. A total of ten different diseases are used for testing, taken from the Machine Learning Repository datasets of the University of California at Irvine (UCI).
Findings
The proposed method improves both the computation time and accuracy of the classification methods used in this paper. Bayesian networks based on experts' knowledge achieve a maximum average accuracy of 87 percent, with a minimum standard deviation average of 0.04 over the sample datasets among all classification methods.
Practical implications
The proposed methodology can be applied to perform disease differential diagnosis analysis.
Originality/value
This study presents the usefulness of experts' knowledge in the diagnosis while proposing an adopted improvement method for classifications. Besides, the Bayesian network based on experts' knowledge is useful for different diseases neglected by previous papers.
Details
Keywords
Tsung-Sheng Chang and Dong-Yih Bau
People have utilized artificial intelligence (AI) reading assistants for study. This tool assists readers in summarizing the content of a book. However, the crucial factor in…
Abstract
Purpose
People have utilized artificial intelligence (AI) reading assistants for study. This tool assists readers in summarizing the content of a book. However, the crucial factor in summarizing book content lies in the quality of the content by generative AI, as this quality affects readers’ willingness to use AI tools as reading aids. This study expands the acceptance architecture for artificially intelligent device use (AIDUA), integrates the concept of generative AI quality and proposes a new model for users’ continuous use of generative AI reading assistants.
Design/methodology/approach
This study employed a quantitative approach. A total of 362 respondents were from Taiwan. This study used partial least squares structural equation modeling (PLS-SEM) to validate, aiming to identify factors influencing users’ continued adoption of AI reading assistants.
Findings
The results show that the quality of AI-generated content and readability significantly influence users’ performance expectations and effort expectancy. However, credibility and representationalness have different effects, impacting effort expectancy but not performance expectancy. These findings underscore the critical role of generative AI quality in shaping user expectations and their continued use of AI reading assistants.
Originality/value
This research is of great significance in examining the quality of generative AI. It establishes a theoretical framework applicable to future research, enabling industry players to understand better the pivotal role of generative AI quality in the operation of information services. And focus on using AI reading assistants, describing the specific use of AI for specific tasks.