Vol 11 Issue 1 January 2023-March 2023

Abstract: A tumor is one of the most dangerous malignancies that may affect human beings. The traditional approach of recognition and categorization of brain tumors by radiologists or clinical experts is by human inspection of medical resonant images (MRI).  This type of approach is time-consuming and tedious and most of the time the result is not accurate. When handling human life, accuracy is highly required, hence the need for the automation of brain tumor detection and classification with better accuracy. In the past, various researchers have proposed different traditional classifiers for detecting brain tumors. In this research paper, our model intends to increase the effectiveness of traditional machine learning algorithms by using the stacking method to combine a set of support vector machines, decision trees, and k-nearest neighbors. These base learners are proposed because of their low computational time complexity. The proposed methodology is divided into modules.  Module 1: MRI Image dataset Acquisition from Kaggle.com, Module 2: Preprocessing and Extraction of Features using GLCM, Module 3: ensemble approach for classification, and finally, Module4 is the evaluation of the results from the classifiers using standard performance evaluation metrics

Keywords: Ensemble, benign, malignant, support vector machines, decision trees, and k-nearest neighbors.

Title: Framework on an Intelligent Ensemble Technique for Brain Tumor Detection and Classification

Author: Abiodun Ipaye, Prof. O. O. Obe, Prof. Thompson

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 91-100

Research Publish Journals

Website: www.researchpublish.com

Published Date: 25-March-2023

Abstract: As the universe finds it challenging to define poverty, the world bank views poverty as anyone living below $2 per day. Government and international organizations are working to eradicate this poverty. The study reviews some research on satellite images on the prediction of poverty through the concept of CNN. The study split the datasets satellite images of four (4) countries: Nigeria, Mali, Malawi, and Ethiopia obtained from Kaggle in 90% for training with 15% of it for validation and 10% for testing. The datasets were analyzed using CNN, VGG16, ResNet50, which shows that the VGG16 model performs better than the other two models with the validation accuracy of 94%, while CNN has 91%. ResNet has the lowest validation accuracy of 62%. The rise of high-resolution satellite images that contain extensive data of regions or countries' patterns, features, and landscapes can be applied to determine the economic livelihood of people or nations. The application of satellite images to the prediction of poverty is much easier, faster, and less expensive compared to more the prediction becomes more accessible. This study recommends the need for the availability of large satellites images for every region or country. Future researchers should focus on satellite images to predict poverty and the application of satellite images in detecting crime, road traffic, agricultural soil, and the like.

Keywords: Convolutional Neural Network, Residual Network, Satellite Images, Architectural Neural Network, Support Vector Machine, Visual Geometry Group.

Title: Poverty Prediction by Using Deep Learning on Satellite Images

Author: Sabeer Saeed, Ibrahim Turkoglu

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 79-90

Research Publish Journals

Website: www.researchpublish.com

Published Date: 24-March-2023

Abstract: Browsers are our portal to the web, and if users want a secure, adequate and smart services, websites need to know some information about their browser, operating system and their hardware device. Modern day browsers have evolved a lot; browsers that provide the beauty of the web also provide a dark side, a rich environment of exploitable information that can identify a device. This is called “device fingerprinting,” which is the technique of identifying visitors of a website and verifying if they are who they claim to be. The idea of fingerprinting is to gather some data that helps to recognize the user amongst others. The data collected could be categorized into three main types: Firstly, the device-related data such as graphics card type, and CPU information. Secondly, the information related to the software such as operating system and browser. Thirdly, the user behavioral data such as the mouse speed and keyboard pattern. Websites used to use cookies for identification, however, there is a new and better methodology nowadays. This paper will show what can be used for device fingerprinting as an alternative to cookies. I conclude that there is always a trade-off between privacy and a good service on the internet.

Keywords: Fingerprints, browsers, uniqueness, verification, personal data, cookies.

Title: Device Fingerprinting and Identification

Author: Omar Khalid Alfaraj

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 71-78

Research Publish Journals

Website: www.researchpublish.com

Published Date: 22-March-2023

Abstract: Growth of technologies, interconnected systems and digitalization, securing data becomes a vital concern to governments and organizations. The value of data enforces these governments and organization to implement huge number of security controls to safeguard their data. In fact, no matter of security controls implemented, there is another important factor might cause attacks, data leakage or service interruption which is “Human”. Human is the main part of Social Engineering which is the art of manipulating people to obtain sensitive information. This type of attack is increasing across the world and impacting many organizations. This research paper is going to define certain aspects of social engineering, types of specific social engineering techniques and required security controls to prevent such social engineering attacks.

Keywords: Social Engineering, Attacks, Criminals, Phishing, Baiting, Tailgating, Should Surfing, Dumpster Diving.

Title: Social Engineering Attacks

Author: Fahad Jasim Alanezi

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 68-70

Research Publish Journals

Website: www.researchpublish.com

Published Date: 20-February-2023

Abstract:  In this paper we examine and evaluate different ways of classifying encrypted network traffic using neural networks. For this purposes we create a dataset with a streaming/non-streaming focus. The dataset comprises seven different classes, five streaming and two non-streaming. The thesis serves as a preliminary proof-of-concept for Napatech A/S. The most desirable approach for Napatech is to classify individual packets upon arrival. Our experiments show that this approach is infeasible due to the content being encrypted and therefore without any distinguishable information. We therefore propose a novel approach where the unencrypted parts of network traffic, namely the headers are utilized. This is done by concatenating the initial headers from a session thus forming a signature datapoint. In experiments using the header-based approach we achieve very promising results, showing that a simple neural network with a single hidden ii layer of less than 50 units, can predict the individual classes with an accuracy of 96.4% and an AUC of 0.99 to 1.00 for the individual classes. The thesis hereby provides a solution to network traffic classification using the unencrypted headers.

Keywords: Deep Learning, Encrypted Traffic, PCA, t-SNE, Neuron Network.

Title: Classification of encrypted traffic using deep learning

Author: Kausar Mia, Md. Tamjeed Monshi, Ms. Shanta Rani Saha, Sonjoy Prosad Shaha, Arnab Saha, Angkur Dhar, Md. Tasnim Forhad Rimon, Sadid mahamud

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 52-67

Research Publish Journals

Website: www.researchpublish.com

Published Date: 19-February-2023

Abstract: This research tends to the development of urban lifestyle. We want to characterize the road standard of Dhaka by measuring the width of roads from an image and found the number of methodologies to perform object measurement. Though the study of the aesthetic characteristics of cities must go beyond concern only for the design of some of their parts such as “boulevards, parks, and civic centers. Identifying objects was contour tracing and a canny edge detection algorithm. Then the object is measured by generalizing the pixel mapping and finding output is matched with the street measurement. The implication in road data and establishing urban Planning prototypes does not exist. The measurement findings in this proposed methodology were then analyzed and based on some criteria the street aesthetics. This research work represents the whole procedure including road image acquisition, pre-processing the image, detecting the road, and measurement of the road from various camera distances. This research work ended up with an accuracy of 96% and we have tried to capture the images with a 90-degree view. We used is quite suitable for a cost-effective solution.

Keywords: Artificial Neural Network, Image Segmentation, Deep Learning, Computer Vision, Convolutional Network.

Title: Street width measurement for urban aesthetics identification in Bangladesh based on Computer Vision

Author: Tariqul Islam, Murad Kabir Md. Rakib, HIMANISH DEBNATH HIMU, Md Maruf Ibna Nasim Nishan, Ramim Hossain, Md. Muktar Ali, MD. Jalal Uddin Rumi Palak, Md. Ashikur Rahman, Ahnaf Tahmid Jamee, Md. Omar Faruq Fahim

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 42-51

Research Publish Journals

Website: www.researchpublish.com

Published Date: 18-February-2023

Abstract: The computer lab is very important to the student’s education. Every institution or university should have this as a key resource, especially for tech-related programs like BS Information Technology and BS Computer Science. The purpose of the study is to evaluate the connection between students with BSs in information technology and computer science's laboratory performance and internship grades. The main goal of the study is whether a student's success in the lab during their first year of college has an impact on how well they do in their practicum or internship. The descriptive-correlational study approach was used to demonstrate the laboratory performance of the SY 2021–2022 BSIT and BSCS graduating class. Performance indicators (PI) and the marks they got from the firms during their internships were used to demonstrate this performance. 35 graduates of the BS in information technology and 16 graduates of the BS in computer science from the academic year 2021–2022 are taking part in this study. It was concluded that there is a strong correlation between laboratory performance and academic internships under corporate supervision. These results contribute to a better significance of performance indicator assessment in laboratory procedures. The second goal is to raise the standards of the quality indicators used to evaluate and track students' computer lab performance. The research recommended integrating academic success and student output at work to create more meaningful data for quality improvement.

Keywords: Practicum, Correlation, Computer Laboratory, Performance Indicators.

Title: Correlation Study between Laboratory Performance and Internship Grades of BS Information Technology and BS Computer Science Students in Lemery Colleges S.Y. 2021-2022

Author: Rindel L. Noche, Lovelita D. De Ramos

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 39-41

Research Publish Journals

Website: www.researchpublish.com

Published Date: 10-February-2023

Abstract: Sign language (SL) is a visual language that people with speech and hearing disabilities use to communicate in their everyday conversations. It is entirely an optical communication language due to its native grammar. Sadly, learning and practicing sign language is not that common in our society; as a result, this research created a prototype for sign language recognition. Hand detection was used to create a system that will serve as a learning tool for sign language beginners. We have created an improved Deep CNN model that can recognize which letter, word, or digit of the American Sign Language (ASL) is being signed from an image of a signing hand. We have extracted the features from the images by using Transfer Learning and building a model using a Deep Convolutional Neural Network or Deep CNN. We have evaluated the proposed model with our custom dataset as well as with an existing dataset. Our improved Deep CNN model gives only a 4.95% error rate. In addition, we have compared the improved Deep CNN model with other traditional methods and here the improved Deep CNN model achieved an accuracy rate of 95% and outperforms the other models.

Keywords: Transfer Learning, Reinforcement Learning, Sign Language, Deep Convolutional Neural Networks, VGG16.

Title: Isolated sign language recognition using hidden transfer learning

Author: Kausar Mia, Tariqul Islam, Md Assaduzzaman, Sonjoy Prosad Shaha, Arnab Saha, Md. Abdur Razzak, Angkur Dhar, Teerthanker Sarker, Al Imran Alvy

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 28-38

Research Publish Journals

Website: www.researchpublish.com

Published Date: 07-February-2023

Abstract: In this paper, based on Jumarie’s modified Riemann-Liouville (R-L) fractional calculus, we find the solution of some type of improper fractional integral.  Change of variable for fractional calculus, integration by parts for fractional calculus, fractional L’Hospital’s rule, and a new multiplication of fractional analytic functions play important roles in this article. In fact, our result is a generalization of the traditional calculus result.

Keywords: Jumarie’s modified R-L fractional calculus, improper fractional integral, change of variable, integration by parts, fractional L’Hospital’s rule, new multiplication, fractional analytic functions.

Title: Evaluating an Improper Fractional Integral Based on Jumarie’s Modified Riemann-Liouville Fractional Calculus

Author: Chii-Huei Yu

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 22-27

Research Publish Journals

Website: www.researchpublish.com

Published Date: 19-January-2023

Abstract: Although Internet has great benefits, and greatly affected the world, especially in the field of scientific research, information dissemination, other than the many services it provides such as e-mail service, file transfer and sharing with others and many other benefits. Everything has its downsides, especially if we exaggerate in its use; the most obvious of these problems is Internet addiction.

Internet addiction is one of the newly emerging and striking problems, and it certainly has reasons behind this addiction, such as the great development in technology in addition to the ease of availability of the Internet, computers, mobile devices, and laptops, so the use of the Internet has increased rapidly. In addition, for some people have become the most important thing in their lives, it has become an addiction.

So in this research we will shed light on “Internet addiction” in terms of its causes, its negatives, the ethics and morals of the Internet, the ethical evaluation of Internet addiction, its symptoms, and in the end we present a vision for treating this problem.

Keywords: Internet, Addiction.

Title: Internet addiction

Author: Mansour Mukhtar Ashkanani

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 3-21

Research Publish Journals

Website: www.researchpublish.com

Published Date: 14-January-2023

Abstract: What are the factors that affect the awareness emails? How do I know if my emails have been read by the employees or not? How can a department protect critical information resources through efficient awareness? What types of procedures work best for an organization? These types of questions are commonly heard nowadays. Strong security awareness programs are the first line of defence against cybersecurity attacks. Because no matter how many tools an organization uses, there is always room for development. In this paper, we will discuss some of the crucial security awareness aspects that could influence behavioural shifts for the better.

Keywords: Information security, Human factor, Cybersecurity, Analysis.

Title: Effective Information Security Awareness Emails

Author: Bayan Almulhim, Rami Alghamdi

International Journal of Computer Science and Information Technology Research

ISSN 2348-1196 (print), ISSN 2348-120X (online)

Vol. 11, Issue 1, January 2023 - March 2023

Page No: 1-2

Research Publish Journals

Website: www.researchpublish.com

Published Date: 05-January-2023