For designing of pavements, California Bearing Ratio (CBR) value is an important parameter which is used to determine the strength of the subgrade soils. However, it is to be mentioned that, CBR test is tedious and laborious. Thus, in the present paper an attempt has been made to develop relationships between CBR and various soil index properties such as specific gravity (G), coefficient of uniformity (Cu), coefficient of curvature (Cc), liquid limit (LL), plastic limit (PL), plasticity index (PI), optimum moisture content (OMC) and maximum dry density (MDD) for alluvial soil in West Bengal, India. Empirical relationships have been proposed for both soaked and un-soaked CBR values as a function of these soil index properties by Genetic Expression Programing (GEP). Further, the same index properties have been used to predict CBR values by artificial neural network (ANN) and krigging method. The results clearly reveals that the GEP and ANN and krigging methods can be successfully used for predicting both the soaked and un-soaked CBR values by using the index properties of soil. Moreover, the developed relationships have been compared with the past available relationships. Furthermore, a multi objective optimization has been carried out for getting maximum CBR values.

No abstract

No abstract

Mining for latent emotions embedded in tweets can offer clues about users' affective state on a broad range of topics ranging from their mental health to political opinions. This paper presents a multi-class supervised learning approach to group tweets into six emotions (joy, sadness, anger, fear, love, and surprise) defined according to the Parrott's framework. After extensive pre-processing, linguistic and metadata features extracted from a corpus of tweets are used to train popular machine learning classifiers. The performance of these classifiers is evaluated using accuracy, sensitivity, and specificity computed based on a multi-class confusion matrix approach. Our framework can detect common emotions of joy and sadness with excellent accuracy (> 90%), anger and fear with moderate accuracy (75% − 85%), and love and surprise with lower accuracy (50% − 60%). Overall, the accuracy of our framework still outperforms that of contemporary approaches for all the six emotions. Further analysis of an example multi-class confusion matrix indicates that lower accuracy values for love and surprise may arise because love is often confused with joy, whereas surprise is mixed up with the positive emotion of joy and the negative emotion of fear. Moreover, this confusion could be attributed to an under-representation of these emotions in the data. This highlights the need for building high-quality, balanced benchmark data sets for training multi-label emotion classifiers.

No abstract