Now showing items 1-20 of 46

    • Accelerating ggplot2 based projection on r-map using NVIDIA GPU 

      Islam, Md. Zahidul; Elahi, Md. Tausif (BRAC University, 2016-08-17)
      With an increasing amount of user and data demands for fast data processing, the optimization of database operations continues to be a challenging work. A common optimization technique is to leverage parallel hardware ...
    • Air pollution monitoring system for smart city 

      Khan, Md. Hasib Bin Hossain; Rahman, Raihan Ur; Arafat, Md. Yeasin; Jony, M. A. Nayem (BRAC Univeristy, 2018)
      Where pollution has become a major problem around the world, air pollution is the most dangerous, shocking and severe pollution among other pollutions e.g. water pollution, soil pollution, noise pollution, light pollution, ...
    • Analyzing CV/resume using natural language processing and machine learning 

      Reza, Md. Tanzim; Zaman, Md. Sakib (BRAC University, 2017)
      This paper proposes a model of extracting important information from the semi-structured text format in a curriculum vitae or resume and ranking it according to the preference of the associated company and requirements. ...
    • Audio recognition using feed forward neural network optimized by principle component analysis 

      Momo, Nusrat Suzana; Abdullah (BRAC University, 2017-04-18)
      In our proposed model we have used PCA as dimension reduction technique and neural network for pattern recognition. Our goal was to recognize audios of two vowels spoken by Parkinson’s disease Patient. The vocal of these ...
    • Bangla text extraction by digital image processing 

      Hoque, A. K. M Rashedul; Pandit, Proma Mrittika; Nasreen, Najia; Raihan, Hasin (2017-12)
      Optical character recognition (OCR) is a technology to extract the text from an image. The main purpose of an OCR is to make editable text documents from different scanned documents, image files or books. In this paper, ...
    • Blood group detection using image processing techniques 

      Rahman, Sakib; Rahman, Md. Atifur; Khan, Fariha Ashraf; Shahjahan, Shabiba Binte; Nahar, Khairun (BRAC University, 2017-12-24)
      Blood grouping is the first and foremost essentiality for many of the major medical procedures. Traditional ways of detecting blood group have remained analogue in this era of digitization and are therefore susceptible to ...
    • Business location recommendation using check-in data 

      Ahmed, Nasim Uddin; Mahmud, Shafayet; Islam, Md. Tawabul; Shoumik, Shadman; Habib, Muhaimin (BRAC University, 2017-08)
      In this era of Social Networks, large amount of data is generated from the users of social media and mobile applications on day to day basis. This data can be useful for the companies as they provide insight into the ...
    • Comparative study of 1D de-noising techniques using induction motor fault signals 

      Lamia, Rehnuma Tasnim; Iqbal, Zafor (BRAC University, 2016-08)
      Removing noise from the original signals has always been challenging. A lot of denoising techniques and algorithms has already been published and are being used now-a-days. But knowing which de-noising method is better ...
    • Crime scene prediction by detecting threatening objects using convolutional neural network 

      Nakib, Mohammad; Khan, Rozin Tanvir; Hasan, Md. Sakibul (BRAC University, 2017-04-13)
      Crime scene prediction without human intervention can have outstanding impact on computer vision. In this paper, we present CNN in the use of detect knife, blood and gun in order to reach a prediction whether a crime has ...
    • Design and implementation of a magic mirror using Kinect 

      Monir, Md. Moniruzzaman; Siddique, Md. Nafis Hasan; Tanni, Afsana Pervin; Hashem, Md. Nahyan Ebn (BRAC University, 2016-08)
      Now a days shopping became a daily essential part of our regular life. When we analysis in both online and going physically in the market we get to come up in a point that everyday people are remaining busy with the shopping ...
    • Design of an interactive smart board using kinect sensor 

      Sarker, Nasrul Karim; Islam, Muhammad Touhidul; Majumder, Md. Shahidul Islam (BRAC University, 2017-08-22)
      Interactive smart board is emerging as a reality all around the globe with the advancement in technology. Our goal is to make a cost efficient interactive smart board with the aid of XBox 360 Kinect Sensor which will ...
    • Detecting anomalies in human eyes using structural similarity index measurement 

      Jahan, Monwar; Rushu, Fazle Rabbi; Tabassum, Subah; Ferdous, Jannatul (Brac University, 2018-12)
      From the idea of anomaly, we come to learn that basically it is an idea of abnormality of eyesight, and interruption on the screen of eyes that does not fit with the rest of the pattern. Whatever we see or the images we ...
    • An effective machine learning approach for sentiment analysis of restaurant reviews 

      Karim, Rabita (BARC University, 2016-08)
      Sentiment analysis or opinion analysis is creating a vast area of research in this modern era of social media. Various blogs and Social Medias (Facebook, twitter, Instagram) are the most popular platform for the users or ...
    • An efficient facial expression recognition method using mean And standard deviation 

      Laboni, Pragna; Zaman, Nusrat (BRAC University, 2017-08-21)
      Facial Expression gives vital information about emotion of human being. It is really a speedily growing and an ever green research field in the sector of computer vision, artificial intelligence and automation. If we talk ...
    • An efficient interpretation model for people with hearing and speaking disabilities 

      Sayeed, M. M. Mahmud; Hossain, Anisha Anjum; Priya, Samrin (BRAC University, 2017-08-22)
      Sign language is a medium of communication between individuals who have hearing and speaking deficiency. Generally they are called Deaf and Mute. To have a better, effective and simpler communication between the vocal and ...
    • An efficient interpretation model for people with hearing and speaking disabilities 

      Sayeed, M. M. Mahmud; Hossain, Anisha Anjum; Priya, Samrin (BRAC Univeristy, 2017-08-22)
      Sign language is a medium of communication between individuals who have hearing and speaking deficiency. Generally they are called Deaf and Mute. To have a better, effective and simpler communication between the vocal and ...
    • Entry restricted security system for a smart home 

      Razi, Abdullah Al; Hossain, Md. Emarat; Rahman, Farah; Shahnawaj, Md. Hossain (BRAC University, 2016-08)
      This report represents a new personal identification method for entry restricted security system. In this proposed method skeleton recognizing feature of Kinect is being used to identify human. Human identification has ...
    • Gesture based implementation on neural network: Bengali sign language to text conversion 

      Hasan, S.M. Farzana; Rahman, Tanjina Mehnaz; Chowdhury, Anika Raisa; Biswas, Akash (BRAC Univeristy, 2017-08)
      This paper presents a novel system that converts Bengali Sign language to text using an optimum system comprising of artificial neural networksand support vector model. Bengali Sign Language, has very few research papers ...
    • Human identification using dental radiograph 

      Fahad, Salem Quddus; Hasan, Md. Nazmul; Sultana, Sharmin; Rabbani, Golam Shams (BRAC University, 2017-12)
      Dental biometrics is a very important feature in human identification. It can help greatly in Forensic Dentistry. In this paper, we present a method for identifying people based on shapes and appearances of their teeth ...
    • A hybrid fake banknote detection model using OCR, face recognition and hough features 

      Zarin, Adiba; Tasnim, Ummay; Jahan, Israt (BRAC University, 2018-08-13)
      Currency duplication is now a common occurrence due to the advancement of printing and scanning technology. Many note detection systems are present in banks but they are very costly. In this paper, we are proposing an ...