Search

As usage of internet varies time to time depending on the modes, minds of users, Telecom services need to understand the tastes or requirements of users and develop a dynamic data analytics solution to sustain in the competitive market. In this paper, we have proposed an approach to data analytics or BI (Business Intelligence) solution taking into account the influence of Bangladeshi people's user experience of mobile data. We have shown the proper separation of analytical reporting and extract-transform-Ioading (ETL) part to easily adopt Serum method for business intelligence report development of telco operators. Serum doesn't mean that always the service delivery will be faster with high accuracy. But, for telco operators service development and delivery should be accurate and faster. Our proposed model is very much capable of obtaining high accuracy and agility at the same time where the same requirement rarely come back to product backlog for having an error in the previous development cycle.

Terrorist organizations use different social media as a tool for spreading their views and influence general people to join their terrorist activities. Twitter is the most common and easy way to reach mass people within a small amount of time. In this paper, we have focused on the development of a system that can automatically detect terrorism-supporting tweets by real-time analyzation. In this system, we have developed a frontend for realtime viewing of the tweets that are detected using this system. We have also compared the performance of two different machine learning classifiers, Support Vector Machine (SVM) and Multinomial Logistic Regression and foundthe first one works better. As our system is highly dependent on data, for more accuracy we added a re-train module. By using this module wrongly classified tweets can be added to the training dataset and train the whole system again for better performance. This system will help to ban the terrorist accounts from twitter so that they can't promote their views or spread fear among general people.

Digital images, being on the verge of its utmost popularity encompasses plenty of applications and as such are generated at an unprecedented rate. These digital form of data are often found with redundant information. Applications that require a bulk amount of images to be processed, turn out to be high regarding computational complexity. Needless to say, it leads to inefficient storage utilization. In this paper, a hybrid approach is applied to compress a large-scale image data-set by combining two popular algorithms: Principal Component Analysis (PCA) and K-means. This paper works with a view to diminishing the redundant information by implementing dimensionality reduction followed by color quantization. The PCA is used to project the data onto a lower dimensional space with retaining as maximum variance as possible. The K-means algorithm is used to restrict the distinct number of colors to represent an image by means of clustering the data together. The results obtained from the proposed method is compared with the results obtained from implementing PCA and K-means clustering algorithms independently, where the proposed method provides with a better compression ratio.

CSE is one of the most encouraging fields with high growth opportunities in the job sectors. Every year we are getting a large number of CSE graduates from public and private universities of Bangladesh as well as the whole world. Each of them tries to get a good job with better salary as early as possible. Several factors (university ranking, CGPA, programming skill, job experience etc.) are connected to get a good job. In this paper, we have analyzed CSE graduates of different universities in job sectors with the help of decision rule. We have collected and analyzed data from ten public and private universities of Bangladesh. We have generated graduate's individual rank and finally produced rank of ten universities. We have applied the Pearson Correlation formula to recommend salary and approximate time estimation to get a job. We evaluated our system several times with the necessary graduate's profile and got a satisfactory result.