2022

Browse

Now showing 1 - 20 of 52

Nuclei Instance Segmentation of Cryosectioned H&E Stained Histological Images using Deep Learning
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-04-30) Ahmed, Zarif; Siddiqi, Chowdhury Nur e Alam; Alam, Fardifa Fathmiul
Nuclei instance segmentation is an important step for oncological diagnosis and pathology research of cancer. HE stained images are considered the gold standard for medical diagnosis. But before being used for segmentation, it is required to pre process them. There are two principle methods to preprocess them formalin-fixed paraffin-embedded samples (FFPE) and frozen tissue samples (FS). Even though FFPE is widely used, it is a time consuming process whereas FS samples can be processed very quickly. But analysis of FS-derived HE stained images can be more difficult as rapid preparation, staining, and scanning of FS sections results in degradation of image quality. Therefore, in this thesis, we explored various state of the art segmentation architectures to create a model that will segment nuclei of FS-derived HE stained images with a high quality feature extraction. Here, we have been working on a novel dataset called CryoNuSeg that contains 30 FS-sectioned images of 10 human organs. It has a benchline score of DICE 80.3 ±4.3, AJI 52.5 5.0, PQ 47.7 6.1. U-Net is the first and most prominent architecture for biomedical image segmentation. We are exploring various U-Net architectures. We have trained Triple U-NET on the dataset using binary masks in place of U-NET keeping all other parts of the instance segmentation algorithm same such as Gaussian Filtering and Watershed Post processing. The results using Triple U-NET crossed all the benchline scores. The triple U-Net architecture gives a score of DICE 80.33, AJI 67.41 and PQ 50.56. We have developed a deep learning model that performs highly accurate nuclei segmentation of FS sections despite degraded image quality for fast oncological diagnosis.
Online Booking System
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2022-05-30) Moindjie, Housnata; Camara, Khalid; Taqi, Ghaith Mansoor
The "Online Booking System" for Atlantic Hotel is an imaginary hotel that uses the internet to reserve hotel rooms and other facilities available within the hotel. The "Online Booking System" project is a system that uses the internet to make reservations for various hotel amenities. The goal of this research is to create and deploy an online hotel reservation system that will replace the manual booking process for various hotel services. The former system for booking hotel services had several issues, such as delays in processing customer bookings or paying for rooms that were below or over the norm, which created a lot of problems in emergency bookings. The system is divided into three (3) main categories; The Administrator who can manage the whole system, the Front Desk Manager can only manage the booking status and the Users (Customers) can do bookings and others activities. The system has web pages that may be accessed with a Web site browser make up the Online Hotel Booking System's interface. PHP (Hypertext Preprocessor) and HTML are used to develop the system (Hyper Text Markup Language). By using the Internet, users can reserve rooms at Atlantic Hotel at any time. For the new system, available rooms and facilities were employed so that the customer could see and choose his room even before arriving, as well as in emergency situations. This innovative solution can help hotel owners manage their properties by allowing them to control receptionist movements and eliminate fraudulent actions. It also enhanced hotel managers' efficiency and profit margins, as they now have better and better facilities. The Online Booking System is a simple system to use. By following its easy and straightforward GUI (Graphical user interface) design, anyone who knows how to use a Web browser can quickly carry out bookings, update booking details, cancel bookings, change personal profiles, examine booking history, or see hotel information.
Land Registration and Ownership Verification application using Blockchain
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2022-05-30) Ahmed, Nafis; Hussain, Md Masuk Al; Nishad, Nowshadul Islam
Our project aims to explore the practicality of using Blockchain in the Land Registration Process and targets to prevent different fraudulent actions by verifying the Identity and Related Documents of the involved parties. In this report, we talk about the existing and proposed architecture of different research publications and analyze their usability on tackling the issues that we face in Bangladesh’s process. But in our version of our project, we tend to make the whole procedure of registration and verification transparent and retain the integrity of the attested documents and information to prevent any sort of tampering.
PointLSTM and Depth-CRNN based Hand Gesture Recognition
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Haque, Amira; Rahman, Mirza Zamiur; Sayera, Reeshoon
Hand gestures represent spatiotemporal body language conveyed by various aspects of the hand, such as the palm, shape of the hand, and finger position, with the aim of conveying a particular message to the recipient. Computer Vision has different modalities of input, such as depth image, skeletal joint points or RGB images. Raw depth images are found to have poor contrast in the region of interest, which makes it difficult for the model to learn important information. Recently, in deep learning-based dynamic hand gesture recognition, researchers have attempted to combine different input modality to improve recognition accuracy. In this paper, we use depth quantized image features and point clouds to recognize dynamic hand gestures (DHG). We look at the impact of fusing depth-quantized features in Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) with point clouds in lstm-based multi-modal fusion networks.
Fake Review Detection Using Machine Learning Techniques
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Bari, Sadat Shahriar; Sakib, Robiul Ahammed; Nico, Nabil Hossain
Nowadays, review sites are increasingly confronted with the spread of disinformation, for example, opinion spam, which aims to promote or harm certain target businesses, by simultaneously deceiving the human readers. For this reason, over the past years, several data-driven approaches have been proposed to assess the credibility of user-generated content delivered through social media in the form of online reviews. Linked to both review and reviewers, as well as the network structure that links separate entities at the review site.This article aims to provide an analysis of various machine learning methods and deep learning methods for analyzing fake user review detection on bangla languages based on the reviewer and review-centric features.Additionally, this work offers to provide a synthesized dataset for fake user review detection in the Bangla language
Medical Image Segmentation Using Attention-based Residual Double U-Net
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2022-05-30) Khan, Akib Mohammed; Khan, Fahim Shahriar; Ashrafee, Alif
A common use case for image segmentation in medical-image-based diagnosis is to help clinicians to focus on a specific area of the disease. Manually inspecting polyps from colonoscopy for colorectal cancer or performing a biopsy on skin lesions for skin cancer are time-consuming, laborious, and complex procedures. Automatic medical image segmentation aims to expedite this diagnosis process. The accuracy of image segmentation has increased due to advancements in machine learning techniques and deep learning models. However, there is still room for improvement as there exist various challenges due to the large variation in the appearance of objects in different sizes with no distinct boundaries. To address these issues, we propose a novel-attention based residual Double U-Net architecture that improves on the currently existing skin lesion segmentation networks. We incorporate attention gates on the skip connections and residual connections in the convolutional blocks of Double U-Net, a state-of-the-art (sota) segmentation network. The attention gates allow the model to retain more relevant spatial information by suppressing irrelevant feature representation from the down-sampling path. At the same time, residual connections help to train deeper models by ensuring better gradient flow. We conducted experiments on three datasets: ISIC 2018 (skin lesion), CVC Clinic-DB (polyp), and the 2018 Data Science Bowl (nuclei) datasets and achieved Dice Coefficient (DSC) scores of 91.64%, 94.35% and 92.45% respectively. Further improvement can be achieved by simplifying the structure of our architecture in order to reduce the number of parameters.
Land Cover and Land Use Detection using Semi-Supervised Learning
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Hossain, Md. Zarif; Lisa, Fahmida Tasnim; Mou, Sharmin Naj
There have been considerable advancements in semi-supervised learning in the remote sensing community. It is a technique that uses a small number of labeled data to train a model. Generally, deep learning networks learn from labeled data only. But since finding a huge corpus of a labeled dataset is rare and manually labeling datasets is timeconsuming and expensive. And labeling remote sensing satellite images is much more challenging than typical image datasets with good accuracy. Our proposed method aims to solve the problem for labelling unlabelled data with better accuracy. We use a SSL technique with a proper class-rebalancing technique to help solve the imbalanced dataset problem. We do it by creating “artificial” labels and training a model to gain reasonable accuracy. Moreover, it is a common occurrence that datasets are typically class-imbalanced. And if they are trained using it, with a high number of samples, the model becomes biased towards the majority classes and away from minority classes having few examples. This becomes a primary problem to the poor performance of an SSL model. We use a distribution alignment strategy to iteratively redistribute the classes through re-sampling. We showed that our proposed method improve a stateof- the-art SSL method with a tweaked augmentation strategy to generate high-quality pseudo-labels, updating the labeled set handling imbalanced data through re-sampling and also can reduce model bias. This is done on various class-imbalanced satellite image datasets. This method consistently outperforms other methods and greatly reduces the need for labeled data and also solves the issue of class imbalance in datasets.
Multi Locale Bone Fracture Radiographs and Localization
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Abedeen, Iftekharul; Rahman, MD Ashiqur; Prottyasha, Fatema Zohra
We introduce MLBFR, a varied radiographs dataset of human bone fractures. The dataset contains 2,583 radiographs, among which 410 have 575 fracture points. A radiologist manually labelled the dataset as ”fractured” and ”non-fractured” with masks for the fracture locations. The dataset was verified and approved by an expert medical officer to evaluate the radiologist’s performance further. To precisely detect and localize the fracture areas, we experimented with several state- of-the-art object detection models, YOLOv5, maskRCNN, efficientDet and more, along with their ensemble. The trained models fell under two criteria, one being the full dataset and the other being only the fractured radiographs. The trained models managed to achieve a precision of 78.9% and 91.65% on combined and only fractured radiographs, respectively. The model performances were comparable to that of radiologists in detecting major abnormalities in the arm and shinbone area. With falling slightly behind in detecting fractures in the hip, thigh, and finger fractures. It is our belief that the task of improving this performance will be a good challenge for future research. To further encourage advancement in this area, we intend to make this dataset freely available in the future.
Study on the Accent Independent Features for Speech Emotion Recognition
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2022-05-30) Tabassum, Nowshin; Tabassum, Tasfia; Safa, Tahiya Sultana
Great progress have been made in speech recognition but we still have a long way to go to have a smooth human-computer interaction because the computer still finds it difficult to understand the emotional state of the speaker. This has introduced a brought into light a relatively recent research field, namely Speech Emotion Recognition. There are some implicit information about the emotions in every speech signal, which can be extracted through speech processing methods. There are many systems proposed in the literature to identify the emotional state through speech. Extraction of features from speech, Selecting a suitable feature set, designing a proper classifications method and preparing an proper dataset are the main points of designing a Speech Emotion Recognition (SER) systems. However despite significant progress in this area there still remains many things which are not well understood, specially, when attention was given to the cultural differences of people. Emotions Recognition in speech can vary from person to person based on their age, gender, language, accents and many other factors. To explore how much accents affect SER, we looked into how the feature varies for different accents in the domain of Speech Emotion Recognition. This paper focuses on the issue if Speech Emotion Recognition is Accent Independent or not. Study on different speech features, experiments on their extraction process and reduction techniques and experiments on selection of accent independent features are carried out. Which will be used to train a model and will lead us to a conclusion if SER depends on accents or not and which of the features of Speech help identify the emotions more accurately despite of the accent.
An Empirical Study on Neophytes of Stack Overflow: How Welcoming the Community is Towards Them
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Mohammad, Suzad; Jobair, Abdullah Al; Maisha, Zahin Raidah
Stack Overflow (SO) is the most popular question and answers (Q&A) platform for programmers with a rapidly expanding community of new users. However, the unwelcoming environment towards new users has been under discussion for several years which is a major concern and hindrance towards the enhancement of a skillful community. In this work, we study a specific group of users who are either registered in the last 45 days or have a reputation less than or equal to 50 and term them as "neophytes". Upon establishing significance of the definition of neophytes, we perform manual analysis of neophytes' posts. We organize our research work into two research questions where we investigate whether neophytes actually face hurdles while collaborating in Stack Overflow and, if so, identify the potential reasons behind this phenomenon by qualitative and quantitative analysis. Our study finds that neophytes are indeed facing hurdles while collaborating in the platform. The reasons behind the hurdles include harsh moderation of posts, negligence of the posts, deleting or closing of posts, downvoting without providing any proper reasoning, etc. Our findings can provide guidelines to create a more user-friendly SO community. Furthermore, this study can guide researchers to observe the reactions of neophytes in adverse situations and recommend some steps for the community to make positive changes to the Stack Overflow environment.
ChartSumm: A large scale benchmark for Chart to Text Summarization
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Rahman, Raian; Hasan, Rizvi; Farhad, Abdullah Al
Information visualization such as bar- and line-charts are quite popular for understanding large tabular data. But, interpreting information solely with different visualization techniques can also be difficult due to different reasons like visual impairment or the requirement of prior domain knowledge to understand the chart. Automatic "chart to text summarization" can be promising and effective tool for providing accessibility as well as precised insights of chart data in natural language. In spite of having a good potential, there have not been a lot of works on chart to text summarization making it a low resource task. Scarcity of large scale datasets for chart to text summarization is one of the reason behind this. The human written descriptions in the available dataset also contains information beyond the knowledge of the chart making it difficult for us to have an unbiased evaluation. In our thesis, we propose ChartSumm a large scale dataset for chart to text summarization consisting of 84,363 charts along with their metadata and descriptions. We also propose two test sets: test-e and test-h for evaluating the performance of the trained models available in this domain. Our experiment shows that a T5 model trained on our dataset has achieved BLEU score of 75.72 in test-e set and 64.78 in test-h set. From our analysis we can conclude that large language models like T5 and BART can generate short precised deception from given chart metadata.
Image Captioning Using Scene Graph and Language Decoder
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2022-05-30) Herok, Asaduzzaman; Ahmed, Kawsar; Masum, Safayet Hossain
Image captioning refers to the task of assigning natural language description to an image from its visual and cognitive information. It’s a multi-modal task where image understanding and natural language generation is the backbone. Real life applications like content based image retrieval, navigation of self driving car, assisting visually impaired people, visual question answering etc. are the areas where image captioning can be used. Even though a significant amount of research work has been done on image captioning, still a lot of works can be done to improve the accuracy of Image captioning systems specially for visually challenged images. We explored the possibilities of developing a more robust and accurate image captioning system that can handle motion blur, plain text tokens, partially visible objects in an image. We proposed a pipeline that includes Global feature extraction for extracting overall pictorial information of the image, Scene Graph for detecting objects and learning individual relationship among the objects, OCR token extractor for understanding the plain text in the image (if available) and an encoder-decoder based language model for features to text translation. The main goal was to exploit the research opportunities and improve the research gap. Finally, we explored the result of our findings and did a comparative analysis of our architecture with existing state-of-the-art papers on VizWiz-Captions dataset since images of this dataset are taken by visually impaired people making images more visually challenged.
Prediction of ECG-Biomarkers for Fetal Arrhythmia Using Non-invasive Fetal ECG
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Ela, Razia Zaman
A noninvasive Fetal Electrocardiogram (ECG) is supposed to be a potential prognostic tool in fetal arrhythmia identification and post-treatment. Fetal ECG data generated cannot be real-time accumulated, processed, and used for enterprise-level healthcare and wellness services with the existing fetal heart monitoring system used in hospitals. This study aims to quantify the ECG biomarkers and predict Fetal arrhythmia using Non-invasive fetal ECG data. We investigated the recordings of a total of 24 pregnant women using the Non-Invasive Fetal ECG Arrhythmia Database (NIFEA DB) (February 19, 2019) from physionet.org. We extracted ECG Fiducial Features and performed various statistical analyses on them to quantify ECG biomarkers. After performing statistical analysis we can conclude that Fetal arrhythmia ECG changes are associated with the ECG fiducial features. Machine-learning algorithms were investigated to predict fetal arrhythmia through Noninvasive Fetal ECG signals. The Overall accuracy of various Machine Learning Models is as followed: C5.0 is 95%, KNN is 94 %, CHAID is 90%, Neural Network is 81 %, and CART is 79 %. A noninvasive Fetal ECG-based Fetal Arrhythmia prediction approach is expected to utilize in a wearable fetus monitoring system.
Sentiment Analysis for Software Engineering; A Study on the Effectiveness of Data Augmentation and Ensembling using Transformer-based Models
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Abid, Muhtasim; Tusar, Zubair Rahman; Sharfuddin, Sadat Bin
Sentiment analysis for software engineering has undergone much research to efficiently develop tools and approaches to classify sentiment polarity for software engineering contents. It started with customized tools based on lexicon and supervised approaches like SentiStrength-SE, SentiCR, and Senti4SD. Pre-trained transformer-based models like BERT, RoBERTa, and XLNet have later outperformed the tools. These models give an improved classification of sentiment polarities for software engineering content when fine-tuned on SE-specific datasets. Although the performance of these models is much better than previously existing tools, there is still much room for improvement, and that is what we have demonstrated in this work. We use three pre-trained transformer-based models on four gold-standard SE-specific datasets and ensemble the models to show the improvement of the ensemble approach over the individual pre-trained transformer-based models. We use two key metrics to assess performance: weighted-average F1 scores and macro-average F1 scores. We also apply text augmentation on the datasets that have some issues like small size and class imbalance and then evaluate the performance of our approaches on the augmented datasets as well. Our results show that the ensemble models outperform the pre-trained transformer-based models on the original datasets and that data augmentation further improve the performance of all the approaches used in the work.
Readability of Code Snippets Included in Stack Overflow Questions: An Exploratory Study
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2022-05-30) Rime, Akib Mahmud; Raiyan, Mohammed Ashfaq; Rani, Nusrat Jahan
Stack Overflow (SO) is a popular question and answer site for programmers of all skill levels. In Stack Overflow software developers asks questions with sample code segments, supporting description, and if needed with bug report. However, the quality of the questioner code is poorly readable to attract the solution of the answerer. In this paper, we explore the idea of Java code readability from Stack Overflow question and tried to investigate the impact of the criteria in code readability. This research is the first study on Java code readability from Stack Overflow that we are aware of. We propose a novel dataset of Java code readability criteria from Stack Overflow. Our study consists of 21 readability metric of Java, 241 SO questions, three human annotators, and two experts. With collecting SO Questions with Java tag from SO site, three human annotators manually evaluated the dataset and later the annotation were rechecked by two software experts. Moreover, we tried to analyse the impact of the criteria in code readability and the correlations between readability and different performance measures of SO site like readability vs score mechanism, readability vs accepted answers, and so on. Finally, we discuss how our study will encourage new inquirer to ask a good readable question so that he can get an answer he was looking for as early as possible.
Data Consistency in Large Scale Applications
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Niloy, Saiful Islam; Ishmum, Md. Nishat; Islam, Md Ariful
One of the challenges in large scale application is data consistency. In this paper, we have studied a few of the algorithms which are used to tackle this issue. We have also conducted some interview sessions with software experts and analyze their judgment regarding this issue. We have tried to analyse this topic based on two major software architecture. Mircoservice and monolithic architecture. Microservice is a trending software architecture for large scale application nowadays. It has many advantages along with some drawbacks. There are many services that communicate with each other to do a single operation. So, maintaining consistency is a big concern here. There are some ways to ensure consistency. Generally, microservice-based application use eventual consistency model. But this model has a chance of data loss. In some cases, data loss can be threatening to the business. To avoid this situation strong consistency model can be used. But algorithms that supports strong consistency comes with performance degradation of software compare to eventual consistency model.
Existence of Security Vulnerable Code Clones in Microservice Systems: An Exploratory Study
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Meem, Maeesha Tasmeem; Muhafiz, Riyad-E-Al; Quasem, Shadid Intisar
Microservice architecture has become one of the most popular emerging trends in software development because of its beneficial features, such as improved scalability, better defect isolation, and increased agility. However, microservices are not devoid of security concerns and code smells such as code clones. The existence of such code clones can cause the propagation and multiplication of security vulnerabilities within and across services. Although researchers have conducted extensive studies on code cloning, the security issues of cloned code in microservices have remained ignored. So, we aim to perform an exploratory study to identify the security vulnerabilities of cloned code in microservices. We performed a quantitative analysis of security vulnerabilities based on Common Weakness Enumeration (CWE) by detecting code clones along with their security issues across eight well-known microservice systems. Our study revealed that code clones in microservices do not comprise a significant amount of security vulnerabilities. However, among the discovered vulnerabilities, some security issues are enlisted in the top 25 most dangerous software weaknesses in the CWE database in 2021. Our study will be helpful in creating awareness among developers so that they can deal with security issues while applying cloning for code reuse purposes.
Semi-Supervised Question Answering with Question-Answer Pair Generation in Bengali
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2022-05-30) Ehsan, Md. Amimul; Shahriar, Md. Shihab; Chowdhury, Ahmad Al Fayad
Although deep learning architectures and large scale datasets have led to great performance on question answering tasks in high resource languages like English, their performance on lower resource languages, like Bengali, is considerably poorer. This is due to the scarcity of labeled data, which can be attributed to the massive amount of human effort and time required to create such datasets. We work towards a translated Stanford Question Answering Dataset (SQuAD) 1.1 in Bengali and ensure that it is of high quality by using a state-of-the-art translation model and a novel embedding based matching approach to properly align the answer spans in the target language (Bengali) in correspondence with the source language, English. We also introduce an end-to-end question answer generation (QAG) system in the Bengali language to generate question answering (QA) datasets for QA models using roundtrip consistency incorporated in a sequence-to-sequence generation task using Googles mT5 model. Additionally, we train 3 different QA models on our Bengali translated dataset achieving EM and F1 scores of 46.1 and 66.2 respectively. Finally, we demonstrate the effectiveness of our QAG model on a sample dataset of news articles in generating domain-specific QA datasets.
SDN-based Time Series Traffic Flow Forecasting in VANET
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh, 2022-05-30) Shuvro, Ali Abir; Khan, Mohammad Shian; Rahman, Monzur
Intelligent Transportation Systems(ITS) provides services for proper traffic assistance. Vehicular Ad-hoc Network(VANET) provides internet connectivity to vehicles and helps in traffic guidance. In this paper, traffic flow prediction is done using a modified transformer architecture for time-series vehicular data. Sequences are generated from the dataset for capturing temporal dependencies. The transformer model has been engineered to capture inter-feature correlations along with inter-sample correlations. Our transformer model has performed much better than other models like LSTM. We also propose a holistic networking model where the vehicles will be connected to Road-side Units(RSUs) and the backbone network will be Software Defined Network(SDN). The traditional design principles, that incorporates data, control and management planes together in a network device, are incapable to adapt with this much data growth, bandwidth, speed, security, scalability compared to SDN as it provides with centralized programmable mechanism reliably. The trained parameters learned using the transformer model will be passed throughout the network for traffic guidance. Similar sized packets are passed using a simulator to demonstrate the time required for the propagation of the parameters.
Early Detection of DDoS Attacks in SDN using Machine Learning Models
(Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh, 2022-05-30) Islam, Refah Rafia; Mahmood, Fahim; Mosharref, Tabia
Software Defined Networks (SDN) are programmable networks that can be easily managed with a global understanding of network topology. However, while the software-defined network architecture enhances network resource pooling by separating the control layer from the data layer, this centralized management and control introduces security vulnerabilities into the SDN architecture. One of the most dangerous attacks that the SDN architecture faces is distributed denial of service (DDoS). Aiming at the detection of DDoS attacks under the SDN architecture, this paper proposes faster DDoS attack detection using machine learning based classifier XGBoost which provides higher accuracy