Browsing by Author "Hafiz, Rubaiya"

Now showing 1 - 9 of 9

A Decision Support System of Selecting Groups (Science/ Business Studies/ Humanities) for Secondary School Students in Bangladesh
(IEEE, 2020-10-15) Hasan, Rifat; Ovy, Md. Khairul Alam; Nishi, Ifrat Zahan; Hakim, Md. Azizul; Hafiz, Rubaiya
As education is the only way to turn a person into human resource, every country tries to give her citizens proper scope of bringing out their inner ability by offering the appropriate education. According to the education system of Bangladesh, an 8 th grade completing student has to choose a group (science, Business Studies, humanity) for further studies. This group will be his/her initial highway for higher education. But it is a matter of sorrow that, in Bangladesh this crucial event is done by some rumors and some traditional old school ways, which are mostly wrong and destructive. From the perspective of this country, the only way of choosing those groups is previous result. Of course, result is one of the most important attribute, but it should not be the only thing. Again in this country, Science is thought to be superior than other groups. That's why, parents have the tendency to impose this group to their children without knowing their ability and interest and leads them towards an uncertain future. Therefore, the aim of this paper is to build a model of group selection by analyzing some random attributes of higher level students who have already gone through this event of selecting groups with the help of data mining and some machine learning algorithms, so that a newly 9 th grade student could have the proper direction of selecting a group which is best for him/her. For the purpose of experimentation we have used three machine learning algorithms: Naïve Bayes, Sequential Minimal Optimization (SMO) and Random Forest. Among these algorithms Random forest gives the best prediction result with an accuracy of 84.9%.
Ascertaining the Fluctuation of Rice Price in Bangladesh Using Machine Learning Approach
(IEEE, 2020-07) Hasan, Md. Mehedi; Zahara, Muslima Tuz; Sykot, Md. Mahamudunnobi; Nur, Arafat Ullah; Saifuzzaman, Mohd.; Hafiz, Rubaiya
Rice is the most grown crop in Bangladesh. It is consumed as the main food course in Bangladesh. The price of rice makes a difference in whether people will eat or starve. To know what's going to happen in the rice market using pen and paper is a far cry as well as time-consuming. Machine Learning (ML) provides the facilities to predict the price of any products to prevent a future collapse in the market. The goal of this paper is to predict the price of rice using Machine learning approach. Data collected from the Ministry of Agriculture website, Bangladesh was used to predict the price. Several machine learning algorithms were used to make this prediction i.e. Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes, Decision Tree and Random Forest. All these algorithms are analyzed to find out which algorithm provides the best performance. Now, we can predict the price of rice, whether it is reasonable, low, or high based on the results achieved by the mentioned algorithms.
CNN Based Automatic Computer Vision System for Strain Detection and Quality Identification of Banana
(2021 International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI), IEEE, 2021-09-08) Al Haque, A. S. M. Farhan; Hakim, Md. Azizul; Hafiz, Rubaiya
Banana is amongst the most appealing and nutritious fruits worldwide, cultivated almost every part of the world round the year. Bangladesh ranks 14 th worldwide in producing this appealing fruit putting a substantial mark on the national economic growth. Classification and recognition of specific strains and identifying the quality of different agricultural products has been a challenge for mass production. With the continuous evolution of technological advancements now it has become a beneficial machine vision task to classify different strains and also determine the quality of the fruit to trash the affected ones that will minimize the loss to a great extent. In this paper, we have proposed a Convolutional Neural Network (CNN) based model that classifies five strains of different bananas namely cavendish, lady finger, shabri, green and the red banana and also identifies the rotten ones with great accuracy. We have successfully deployed the two deep learning models to find significant accuracy varying different parameters. We have also utilized the widely accepted precision, recall, F1-score and ROC evaluation metrics. The second model has outperformed the other in terms of accuracy with 93.4±0.8% and identifying the rotten bananas with an accuracy of 98.3±.8%.
Crime Detection and Criminal Recognition to Intervene in Interpersonal Violence Using Deep Convolutional Neural Network with Transfer Learning
(International Journal of Ambient Computing and Intelligence, 2021) Haque, Mohammad Reduanul; Hafiz, Rubaiya; Al Azad, Alauddin; Adnan, Yeasir; Akter, Sharmin; Khatun, Amina; Uddin, Mohammad Shorif
Interpersonal violence, such as physical and sexual abuse, eve-teasing, bullying, and taking hostages, is a growing concern in our society. The criminals who directly or indirectly committed the crime often do not go into the trial for the lack of proper evidence as it is very tough to collect photographic proof of the incident. A subject's corneal reflection has the potentiality to reveal the bystander images. Motivated with this clue, a novel approach is proposed in the current paper that uses a convolutional neural network (CNN) along with transfer learning in identifying crime as well as recognizing the criminals from the corneal reflected image of the victim called the Purkinje image. This study found that off-the-shelf CNN can be fine-tuned to extract discriminative features from very low resolution and noisy images. The procedure is validated using the developed datasets comprising six different subjects taken at diverse situations. They confirmed that it has the ability to recognize criminals from corneal reflection images with an accuracy of 95.41%.
Forecasting of Inflation Rate Contingent on Consumer Price Index
(Scopus, 2021) Momo, Shampa Islam; Riajuliislam, Md; Hafiz, Rubaiya
Variations of inflation rate possess a diverse influence on the economic growth of any country. Inflation rate control can be accommodated to stabilize the financial aspect’s condition, including the political area. The way to restrain the inflation rate is the prediction of the inflation rate. This paper proposes forecasting the inflation rate by applying machine learning algorithms: support vector regression (SVR), random forest regressor (RFR), decision tree, AdaBoosting, gradient boosting, and XGBoost. These algorithms are employed since the predicting value is nonlinear and complex. Moreover, the regression and boosting algorithms confer good accuracy, as inflation is a frequent dynamic variable that depends on several factors. The models show decent accuracy using the elements consumer price index (CPI), food, non-food, clothing-footwear, and transportation. Among the models, AdaBoost retrospectives the most desirable outcome with the lowest MSE value of 0.041.
Image-Based Soft Drink Type Classification and Dietary Assessment System Using Deep Convolutional Neural Network with Transfer Learning
(Daffodil International University, 2020-09-09) Hafiz, Rubaiya; Haque, Mohammad Reduanul; Rakshit, Aniruddha; Uddin, Mohammad Shorif
Nowadays, people are taking soft drinks (carbonated nonalcoholic beverages) at an increasing rate. Health experts around the world have cautioned from time to time that these drinks lead to weight gain, raise the risk of non-communicable diseases, and so on. To develop consciousness among people, the present work describes an image-based tool to self-monitor the nutritional information of soft drinks by using a deep convolutional neural network (CNN) along with transfer learning. At first, a pre-processing function is done through noise reduction and contrast enhancement. Then the location of the drinks region is extracted through visual saliency and mean-shift segmentation technique. After removing backgrounds and segment out only the region of interest from the image a deep CNN-based transfer learning model is employed for the drink classification. Finally, the size of each drink bottle is estimated using the bag-of-feature (BoF) and distance ratio calculation to find the nutrition value from the nutrition fact table. To perform experimentation a dataset is built containing ten most consumed soft drinks in Bangladesh using images from the ImageNet dataset, internet sources and also self-capturing. The experiment confirms that our system can detect and recognize different types of drinks with an accuracy of 98.51%.
Image-based Soft Drink Type Classification and Dietary Assessment System Using Deep Convolutional Neural Network with Transfer Learning
(Journal of King Saud University - Computer and Information Sciences, 2020-09-09) Hafiz, Rubaiya; Rakshit, Aniruddha; Uddin, Mohammad Shorif; Haque, Mohammad Reduanul
Nowadays, people are taking soft drinks (carbonated nonalcoholic beverages) at an increasing rate. Health experts around the world have cautioned from time to time that these drinks lead to weight gain, raise the risk of non-communicable diseases, and so on. To develop consciousness among people, the present work describes an image-based tool to self-monitor the nutritional information of soft drinks by using a deep convolutional neural network (CNN) along with transfer learning. At first, a pre-processing function is done through noise reduction and contrast enhancement. Then the location of the drinks region is extracted through visual saliency and mean-shift segmentation technique. After removing backgrounds and segment out only the region of interest from the image a deep CNN-based transfer learning model is employed for the drink classification. Finally, the size of each drink bottle is estimated using the bag-of-feature (BoF) and distance ratio calculation to find the nutrition value from the nutrition fact table. To perform experimentation a dataset is built containing ten most consumed soft drinks in Bangladesh using images from the ImageNet dataset, internet sources and also self-capturing. The experiment confirms that our system can detect and recognize different types of drinks with an accuracy of 98.51%.
Real-time Bangladeshi Currency Detection System for Visually Impaired Person
(2019 International Conference on Bangla Speech and Language Processing, ICBSLP 2019, IEEE, 2020-05-13) Sarker, Md. Ferdousur Rahman; Raju, Md. Israfil Mahmud; Marouf, Ahmed Al; Hafiz, Rubaiya; Hossain, Syed Akhter; Protik, Munim Hossain Khandker
This paper presents a real-time Bangladeshi currency detection system for visually impaired persons. The proposed system exploits the image processing algorithms to facilitate the visually impaired people to prosperously recognize banknotes. The recent banknotes of Bangladesh have blind embossing or blind dots, which could be effective to recognize the value of the bill by touching. As the embossing fades away in the long-term used notes, detecting right value of the banknote using image processing algorithms could be considered as a challenging task. Particularly in Bangladesh, each banknote seems similar using the direct exertion of simplified image processing algorithms. In this paper, a recognition system was implemented that can detect Bangladeshi banknote in different viewpoints and scales. The detection system is also able to detect currency those are rumpled, decrepit or even worn. The detection system includes image preprocessing, image analysis and image recognition. To enhance the determination of currency recognition, the descriptor of an individual input scene is matched with various training images of the same category. After that, by analyzing their matching result it recognizes the currency with higher confidence. For real-time recognition, we have deployed the system into a mobile application.
Solving Onion Market Instability by Forecasting Onion Price Using Machine Learning Approach
(Scopus, 2020) Hasan, Md. Mehedi; Zahara, Muslima Tuz; Sykot, Md. Mahamudunnobi; Hafiz, Rubaiya; Mohd. Saifuzzaman
Price is the key factor in financial activities. Unexpected fluctuation in price is the sign of market instability. Nowadays Machine learning provides enormous techniques to forecast price of products to cope up with market instability. In this paper, we look into the application of machine learning approach to forecast the price of onion. The forecast is based on the data collected from Ministry of Agriculture, Bangladesh. For making prediction we used machine learning algorithms e.g. K- Nearest Neighbor (KNN), Naïve Bayes, Decision Tree, Neural Network (NN), Support Vector Machine (SVM). Then we assessed and compared our techniques to find which technique provides the best performance in term of accuracy. We find all of our techniques provide analogous performance. By above mentioned techniques we seek to classify whether the price of onion would be preferable (low), economical (mid), expensive (high).