Browsing by Author "Sohan, Md Fahimuzzman"

Now showing 1 - 5 of 5

A Survey on Deepfake Video Detection Datasets
(Institute of Advanced Engineering and Science (IAES), 2023-11) Sohan, Md Fahimuzzman; Hasan, Md Aumit
Deepfake video has usefulness in entertainment and multimedia technology, however, the danger of deepfake is significant to the social, economical, and political sectors so far. Specifically, to diverge any public opinion by generating fake news and spreading misleading information, national security may be under risk due to misrepresenting statements given by political leaders. The creation of such manipulated videos are getting easier day by day and at the same time it is necessary to detect and prevent them. In order to do that, researchers are creating challenging fake video databases for artificial intelligence (AI) based detection models to contribute to the research. This paper reviewed the existing deepfake video detection datasets available online and used in the previous research articles. We analyzed the literature from two different perspectives, datasets and detection models. The goal of this study is to introduce all publicly available datasets in this field including the discussion of techniques used to generate the data. In addition to our contribution, we showed a result comparison among different deepfake datasets and discussed the findings.
Assessing the Effect of Imbalanced Learning on Cross-project Software Defect Prediction
(10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019, IEEE, 2019-07-08) Sohan, Md Fahimuzzman; Jabiullah, Md Ismail; Rahman, Sheikh Shah Mohammad Motiur; Mahmud, S M Hasan
Software Defect Prediction (SDP) identifies the defect-prone modules from software source code, which helps to serve good quality software. Mostly previous cross-project SDP models were built based on single project data, where single project was used to prepare prediction models. However, this investigation represents an empirical study of SDP where multiple projects data have been used to prepare prediction models. In this study, multiple projects data have been used to prepare a balance and an imbalance datasets. After that this datasets have been used in different prediction models with eight different classifier algorithms. The trained models have been cross-checked by one balanced and imbalanced test datasets. Five evaluation metrics have been considered for evaluating the performance of the models. The experimental results show that there was no significant changes observed between balanced and imbalanced training models. Only AUC (Area Under the Curve) scores have increased significantly in terms of balanced training model with imbalanced test datasets. In the same training model with the balanced test, accuracy and AUC score have increased significantly. However, this study covers widely by creating the classification model from multiple projects' historical data. Further, it proves that if the sufficient number of non-defective and defective data are supplied in the prediction model, it can predict balanced and imbalanced both categories dataset alike. Here, recommendation will be to consider the imbalanced learning while building the prediction model for cross-projects.
NStackSenti
(Communications in Computer and Information Science, Springer, 2019-11-24) Sohan, Md Fahimuzzman; Rahman, Sheikh Shah Mohammad Motiur; Munna, Md Tahsir Ahmed; Allayear, Shaikh Muhammad; Rahman, Md. Habibur; Rahman, Md. Mushfiqur
Sentiment Detection plays a vital role worldwide to measure the acceptance level of any products, movies or facts in the market. Text vectorization (converting text from human readable to machine readable format) and machine learning algorithms are widely used to detect the sentiment of users. This paper presents and evaluates a multi-level architecture based approach using stacked generalization technique named NStackSenti. The presented approach enables the combination of machine learning algorithms to improve the accuracy of detection. Here, Extremely Randomized Tree (ET), Random Forest (RF), Gradient Boost (GB), ADA Boost (ADA), Decision Tree (DT) are used as base classifiers and XGBoost classifier is used as meta estimator. The NStackSenti is applied on two separate datasets to demonstrate the effectiveness in terms of accuracy. NStackSenti provides better accuracy with trigram than unigram and bigram. It provides 83.7% and 86.24% accuracy on 2000 and 50000 data respectively.
Prevalence of Machine Learning Techniques in Software Defect Prediction
(Scopus, 2020) Sohan, Md Fahimuzzman; Kabir, Md Alamgir; Rahman, Mostafijur; Bhuiyan, Touhid; Jabiullah, Md Ismail
Software Defect Prediction (SDP) is a popular research area which plays an important role for software quality. It works as an indicator of whether a software module is defect-free or defective. In this study, a review has been conducted from January 2015 to August 2019 and 165 articles are selected in the area of SDP to know the prevalence of Machine Learning (ML) techniques. These articles are collected by searching in Google Scholar, and they are published in various platforms (e.g., IEEE, Springer, Elsevier). Firstly the information has been extracted from the collected particles, and then the information has been pre-processed, categorized, visualized, and finally, the results have been reported. The result shows the most frequently used data sets, classifiers, performance metrics, and techniques in SDP. This investigation will help to find the prevalence of ML techniques in SDP and give a quick view to understand the trends of ML techniques in defect prediction research.
Training Data Selection Using Ensemble Dataset Approach for Software Defect Prediction
(Scopus, 2020) Sohan, Md Fahimuzzman; Kabir, Md Alamgir; Rahman, Mostafijur; Mahmud, S. M. Hasan; Bhuiyan, Touhid
Cross-project defect prediction (CPDP) is using due to the limitation of within project defect prediction (WPDP) in Software Defect Prediction (SDP) research. CPDP aims to train one project data to predict another project using the machine learning technique. The source and target projects are different in the CPDP setting, because of various structured source-target projects, sometimes it may not be a perfect combination. This study represents a categorical data set ensemble technique, where multiple data sets have been aggregated for source data instead of using a single data set. The method has been evaluated on nine data sets, taken from the publicly accessible repository with two performance indicators. The results of this data set ensemble approach show the improvement of the prediction performance over 65% combinations compared with traditional CPDP models. The results also show that same categories (homogeneous) train-test data set pairs give high performance; otherwise, the prediction performances of different category data sets are mostly collapsed. Therefore, the proposed scheme is recommended as an alternative to predict defects that can improve the prediction of most of the cases compared with traditional cross-project SDP models.