Now-a-days Cluster computing has become a crying need for the processing of large scale data. For computing large amount of data, which need huge execution time, the run time can be reduced using multiple processors and task distribution through cluster computing. It is the technique of sharing two or more computers' resources through a network (usually through a local area network) in order to take advantage of the parallel processing power of those computers. Clusters of computers are usually deployed to improve processing speed and/or reliability and scalability over that provided by a single computer. In this paper we proposed a High Performance computing approach on Linux platform (Ubuntu) using Parallel Programming environment with the collaboration of multiple nodes for large scale computational work.

Now-a-days Machine learning approach is used to solve many problems where intelligence is involved. Lots of time consuming task are done by computers with the power of statistics. In this paper, a machine learning based candidate selection procedure is proposed and implemented for a particular field. A huge amount of activity is involved in the job recruitment procedure. To reduce the manual task a probabilistic machine learning approach is described in this paper. A popular machine learning approach named Naive Bayes Classifier is used to implement the method. Baseline criteria selection depends on the recruiters demand. The proposed system learns from training dataset and produces a short listed eligible list based on learning. The more perfectly one feed the system result will be more accurate.

While strides have been made in deep learning based Bengali Optical Character Recognition (OCR) in the past decade, absence of large Document Layout Analysis (DLA) datasets has hindered the application of OCR in document transcription, e.g., transcribing historical documents and newspapers. Moreover, rule-based DLA systems that are currently being employed in practice are not robust to domain variations and out-of-distribution layouts. To this end, we present the first multidomain large Bengali Document Layout Analysis Dataset: BaDLAD. This dataset contains 33, 695 human annotated document samples from six domains -i) books and magazines ii) public domain govt. documents iii) liberation war documents iv) new newspapers v) historical newspapers and vi) property deeds; with 710K polygon annotations for four unit types: text-box, paragraph, image, and table. Through preliminary experiments benchmarking the performance of existing state-of-the-art deep learning architectures for English DLA, we demonstrate the efficacy of our dataset in training deep learning based Bengali document digitization models.

No abstract