This paper presents a requirement engineering for developing an e-coaching environment in the higher education sector. This research demonstrates that IT experts encounter challenges in establishing a system that matc...This paper presents a requirement engineering for developing an e-coaching environment in the higher education sector. This research demonstrates that IT experts encounter challenges in establishing a system that matches a university’s expectations, as they are usually uncertain about its goals and system requirements. The paper illustrates a business goal-focused requirement induction technique, which encompasses demonstrating the business procedures through Business Process Modelling Notation (BPMN), assessing the university goals via the tree diagram, and drawing out the system requirements from the university objectives through UML state diagrams. A case study of supporting the development of a new IT course is used as a case study and applied using BPMN.展开更多
Text classification of low resource language is always a trivial and challenging problem.This paper discusses the process of Urdu news classification and Urdu documents similarity.Urdu is one of the most famous spoken...Text classification of low resource language is always a trivial and challenging problem.This paper discusses the process of Urdu news classification and Urdu documents similarity.Urdu is one of the most famous spoken languages in Asia.The implementation of computational methodologies for text classification has increased over time.However,Urdu language has not much experimented with research,it does not have readily available datasets,which turn out to be the primary reason behind limited research and applying the latest methodologies to the Urdu.To overcome these obstacles,a mediumsized dataset having six categories is collected from authentic Pakistani news sources.Urdu is a rich but complex language.Text processing can be challenging for Urdu due to its complex features as compared to other languages.Term frequency-inverse document frequency(TFIDF)based term weighting scheme for extracting features,chi-2 for selecting essential features,and Linear discriminant analysis(LDA)for dimensionality reduction have been used.TFIDF matrix and cosine similarity measure have been used to identify similar documents in a collection and find the semantic meaning of words in a document FastText model has been applied.The training-test split evaluation methodology is used for this experimentation,which includes 70%for training data and 30%for testing data.State-of-the-art machine learning and deep dense neural network approaches for Urdu news classification have been used.Finally,we trained Multinomial Naïve Bayes,XGBoost,Bagging,and Deep dense neural network.Bagging and deep dense neural network outperformed the other algorithms.The experimental results show that deep dense achieves 92.0%mean f1 score,and Bagging 95.0%f1 score.展开更多
A complex product subjects to multiple failure modes such as minor and catastrophic failure with some probability.This paper investigates the effects of minor failure and catastrophic failure on the periodic replaceme...A complex product subjects to multiple failure modes such as minor and catastrophic failure with some probability.This paper investigates the effects of minor failure and catastrophic failure on the periodic replacement policy for a complex product supported by a warranty period.Cost models are developed and the expected optimal replacement policies are developed analytically such that long run expected life-cycle cost rate is minimized.Structural properties of the optimal replacement policies are derived for a product which fails with multiple failure modes and the failure rate is an increasing function of time.Finally,a numerical experiment is performed to show the important features of our study.展开更多
Hierarchical time series arise in manufacturing and service industries when the products or services have the hierarchical structure,and top-down and bottomup methods are commonly used to forecast the hierarchical tim...Hierarchical time series arise in manufacturing and service industries when the products or services have the hierarchical structure,and top-down and bottomup methods are commonly used to forecast the hierarchical time series.One of the critical factors that affect the performance of the two methods is the correlation between the data series.This study attempts to resolve the problem and shows that the top-down method performs better when data have high positive correlation compared to high negative correlation and combination of forecasting methods may be the best solution when there is no evidence of the correlationship.We conduct the computational experiments using 240 monthly data series from the‘Industrial’category of the M3-Competition and test twelve combination methods for the hierarchical data series.The results show that the regression-based,VAR-COV and the Rank-based methods perform better compared to the other methods.展开更多
文摘This paper presents a requirement engineering for developing an e-coaching environment in the higher education sector. This research demonstrates that IT experts encounter challenges in establishing a system that matches a university’s expectations, as they are usually uncertain about its goals and system requirements. The paper illustrates a business goal-focused requirement induction technique, which encompasses demonstrating the business procedures through Business Process Modelling Notation (BPMN), assessing the university goals via the tree diagram, and drawing out the system requirements from the university objectives through UML state diagrams. A case study of supporting the development of a new IT course is used as a case study and applied using BPMN.
文摘Text classification of low resource language is always a trivial and challenging problem.This paper discusses the process of Urdu news classification and Urdu documents similarity.Urdu is one of the most famous spoken languages in Asia.The implementation of computational methodologies for text classification has increased over time.However,Urdu language has not much experimented with research,it does not have readily available datasets,which turn out to be the primary reason behind limited research and applying the latest methodologies to the Urdu.To overcome these obstacles,a mediumsized dataset having six categories is collected from authentic Pakistani news sources.Urdu is a rich but complex language.Text processing can be challenging for Urdu due to its complex features as compared to other languages.Term frequency-inverse document frequency(TFIDF)based term weighting scheme for extracting features,chi-2 for selecting essential features,and Linear discriminant analysis(LDA)for dimensionality reduction have been used.TFIDF matrix and cosine similarity measure have been used to identify similar documents in a collection and find the semantic meaning of words in a document FastText model has been applied.The training-test split evaluation methodology is used for this experimentation,which includes 70%for training data and 30%for testing data.State-of-the-art machine learning and deep dense neural network approaches for Urdu news classification have been used.Finally,we trained Multinomial Naïve Bayes,XGBoost,Bagging,and Deep dense neural network.Bagging and deep dense neural network outperformed the other algorithms.The experimental results show that deep dense achieves 92.0%mean f1 score,and Bagging 95.0%f1 score.
基金This work was supported by the National Natural Science Foundation of China under grant numbers 71531010 and 71831006.
文摘A complex product subjects to multiple failure modes such as minor and catastrophic failure with some probability.This paper investigates the effects of minor failure and catastrophic failure on the periodic replacement policy for a complex product supported by a warranty period.Cost models are developed and the expected optimal replacement policies are developed analytically such that long run expected life-cycle cost rate is minimized.Structural properties of the optimal replacement policies are derived for a product which fails with multiple failure modes and the failure rate is an increasing function of time.Finally,a numerical experiment is performed to show the important features of our study.
基金This work was supported by Program of Shanghai Subject Chief Scientist[16XD1401700]National Natural Science Foundation of China[71421002].
文摘Hierarchical time series arise in manufacturing and service industries when the products or services have the hierarchical structure,and top-down and bottomup methods are commonly used to forecast the hierarchical time series.One of the critical factors that affect the performance of the two methods is the correlation between the data series.This study attempts to resolve the problem and shows that the top-down method performs better when data have high positive correlation compared to high negative correlation and combination of forecasting methods may be the best solution when there is no evidence of the correlationship.We conduct the computational experiments using 240 monthly data series from the‘Industrial’category of the M3-Competition and test twelve combination methods for the hierarchical data series.The results show that the regression-based,VAR-COV and the Rank-based methods perform better compared to the other methods.