Internet and social media: Exploring new business models for corporate success
Today, Companies are discovering internet a great marketing prospect and social media a valuable brand promotional proposal. While the companies use these digital platforms as a global window to search for talent, marketers are scanning the medium to drive products and are using it for objective market research. Compared with traditional media, these innovative media allows customers to give their feedback and at times be a part of the product design process, too. Internet, especially social media, has proved to be vastly constructive for businesses for reducing costs, improving customer services and creating an online profile of the business.
Published by: Rakesh Ranjan
Author: Rakesh Ranjan
Paper ID: V4I2-1742
Paper Status: published
Published: April 17, 2018
Effect of strength properties of concrete waste materials (wood powder)
The use of high strength1 concrete is expected to increase as we move into next century in all areas of the world. In recent years there has been a rapid growth of interest in high strength concrete. Concrete is a material used in building construction, consisting of a fine aggregate and a coarse aggregate that is bounded by cement and water with various types of admixtures2 which are available in the market or from the waste materials3. A design mix is specified by the designer principally in terms of strength cement content and water-cement. Since economical parameters and compressive strength are fundamental properties of concrete in two different stages of production, the correlation between costing parameters and compressive strength4 has been used instead of using water-cement ratio versus compressive strength relationship. If we maintain the water-cement ratio and by adding various types of admixtures in concrete we can improve the compressive strength of concrete and also get more strength which will be very economical. In the proposed method, The designer is able to estimate parameters like compressive strength and economical costing at the design stage for a given target strength, in addition to ingredients5 of concrete
Published by: Kashish Arora
Author: Kashish Arora
Paper ID: V4I2-1817
Paper Status: published
Published: April 17, 2018
Object recognition using CNN
Object recognition is a popular task in computer vision. The method usually requires the presence of a data-set annotated with location information of the objects, which is in the form of bounding boxes around the objects. In this project, we have implemented a method to carry out object recognition in a weakly supervised manner i.e., using partially annotated data-set. The data-set provides the information about what objects are present in the image but not where they are present. We have used a Convolutional Neural Network(CNN) based architecture to perform this task. We also validated by experimenting with different architectures that mere information of presence/ absence of objects in an image (weak labels) does provide their location information for free.
Published by: Jagruti Jadhav, Mehzabeen Attar, Shradha Patil, Saleem Beg
Author: Jagruti Jadhav
Paper ID: V4I2-1827
Paper Status: published
Published: April 17, 2018
A study on classifiers performance for prediction of diabetic disorder
In recent years, there has been an explosion in the rate of using technology that helps in discovering the diseases. It contributes to treating several complications such as nerve and blood vessel damage, heart problems, and a higher risk of kidney malfunctioning. Data Mining, being the foremost analyzing technique used by researchers that provides effective results in an early diagnosis of diabetes. This research paper focuses on the approaches, namely Decision tree, Naive Bayes and Neural-Fuzzy classifier in predicting disease and their performance is measured using Accuracy evaluation metric. The classification accuracy and response time were compared to the methods using Accuracy and Running Time as Performance criteria. From the study, it is observed that the Decision tree algorithm gives a better accuracy in the overall performance of the classifier among the algorithms under consideration.
Published by: R. Pradeepa, K. Palanivel
Author: R. Pradeepa
Paper ID: V4I2-1887
Paper Status: published
Published: April 17, 2018
Food recipe application
The proposed project is an Android Application that will provide recipes to the users based on the ingredients available to them. From a list of ingredients, the user has to select the available ingredients and then the application will display a list of recipes which will use the ingredients selected by the user. The user will have filters to select the kind of recipe it wants and then the result can be sorted and filtered according to the user’ needs.
Published by: Hanish Punamiya, Mitesh Jain, Saumil Mavani, Ajay Dhruv
Author: Hanish Punamiya
Paper ID: V4I2-1896
Paper Status: published
Published: April 17, 2018
Grassberger procaccia algorithm for EEG channel selection
The multi-channel nature of EEG a data poses a big challenge to the development of automatic EEG analysis and classification systems. Due to the “curse of dimensionality” problem, the analysis and classification of several channels may not lead to the desired performance. Accordingly, a number of algorithms have been proposed to identify small ”static” subsets of channels that are capable of differentiating between samples of different classes. However, the identification of small subsets of relevant channels may not always be possible, where for certain applications the smaller the number of channels the less chance that sufficient information is provided. The propose in this project is a dynamic channel selection using GrassbergerProcaccia algorithm that identifies a channel (or a subset of channels) for each time segment of the signal that is relevant to the class of that particular time segment. To achieve this, we embraced the Grassberger–Procaccia algorithm methodology, and particularly the multiple classifier behaviour approaches. Each EEG channel can be chosen to represent a certain unseen time segment of the signal based on the performance, or local accuracy, of its nearest neighbors in the set of training time segments. Results obtained using EEG data from a four-class alertness state classification problem reveal that the proposed approach is capable of achieving competitive performance compared to a traditional static channel selection based method. The algorithm also produced very encouraging results when a method developed by Grassberger Procaccia allows estimation of the dimensional complexity of the state‐space attractor of a time series. Saturation of dimensional‐complexity estimates with increasing values of embedding dimension is considered a strong indication that the time series is governed by deterministic chaos. The present investigation employed the Grassberger‐Procaccia method to estimate EEG dimensional complexity in a multi‐subject, factorial experiment.
Published by: K. Navitha, Shaista Simmeen, K. Likhitha, Jigar Patel
Author: K. Navitha
Paper ID: V4I2-1953
Paper Status: published
Published: April 17, 2018
