STM Journals Peer-reviewed research from Consortium e-Learning Network

3 publications

  • Published Subscription

    Effect of Rank Based Correlation on K-Nearest Neighbour

    By Nazmul Shahadat, Abu Naem, Rasel Dewan

    Abstract: AbstractBecause of its simplicity, higher efficiency and effectiveness, K-nearest neighbour (KNN) isthe most popular and chosen algorithm in the last few years. It has many conveniences withthe exception of some inconvenience. In this study, we explore the correlation and dependencebetween attributes, and try to significantly improve the classification accuracy from existingalgorithm by skipping correlated attributes. To get classification accuracy, we applied thisskipping correlated attributes method in KNN ranking based classifier. …

    Published in Current Trends in Information Technology · Vol. 7, Issue 2, 2017 · pp. 17–22 Read article

  • Published Subscription

    Performance Evaluation of PCA Based Back Propagation over PCA Based Euclidian Distance for Video Images

    By Nazmul Shahadat, Dardina Tasmere Tonu, Shyla Afroge

    Abstract: Key frame selection aims at reducing amount of data and retrieve information desired from a video. Video summarization aims at reducing the amount of data in order to retrieve information from a video. In this paper, we present an innovative approach for key frame selection; and a face detection and recognition from video sequence. For face detection from video, first we select the key frames and then detect multiple faces …

    Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 3, Issue 1, 2016 · pp. 24–31 Read article

  • Published Subscription

    Strategies to Control Quality in Crowdmining

    By Md Rafiqul Islam, Bushra Rahman, Nazmul Shahadat, Dardina Tasmere

    Abstract: Normal 0 false false false EN-US X-NONE X-NONE MicrosoftInternetExplorer4 Crowd sourcing is emerging as an effective method for data gathering and analysis, which introduces a new paradigm of data mining process. Crowd workers perform small chunks of larger tasks in return for a reward, which can be monetary, material, psychological and so on. One of the biggest challenges of crowd mining is controlling the quality of the answers collected from …

    Published in Current Trends in Information Technology · Vol. 6, Issue 1, 2016 · pp. 1–5 Read article

Support