Publications
Integrating Three Machine Learning Algorithms in Ensemble Learning Model for Improving Content-based Spam Email Recognition
Dec 18, 2024Journal Journal of Soft Computing and Data Mining (JSCDM)
Publisher Universiti Tun Hussein Onn Malaysia
DOI https://doi.org/10.30880/jscdm.2024.05.02.014
Issue Vol. 5 No. 2 (2024)
Volume 5
Email spam refers to junk files, images, or data sent through email that might contain links leading to phishing websites. This email is often sent repeatedly to random users, and sometimes it may be dangerous. The objective of this study is to predict and recognize whether the emails sent to users are spam or not by using machine learning classification algorithms. Email Spam Classification (ESC) datasets are used in this study for spam detection tests. The ESC datasets contain 5172 rows and 3002 columns of spam and non-spam features. The methodology used in this study is the CRISP-DM to guide the process of evaluating the performance of three machine learning algorithms: Naive Bayes (NB), Logistic Regression (LR), and Random Forest (RF). Subsequently, an ensemble model that integrates the three machine learning algorithms is proposed to improve the performance of spam email recognition. The selected evaluation metrics are F1-Score, accuracy, precision, and recall. Based on the results, the RF algorithm has the highest accuracy of 97.3% in classifying spam emails, with an F1 score of 96.8%, precision of 96.2%, and recall of 96.0%. The NB achieves the best second results, which are slightly different from the RF, and the LR achieves considerably lower results than the other two algorithms. The ensemble model that integrates the three algorithms performs best in classifying spam emails with 98.9% accuracy, 97.6% precision, 97.4% recall, and 96.7% F1-score.
Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision Transformers
Sep 15, 2022Journal The Majlesi Journal of Electrical Engineering (MJEE)
Publisher Islamic Azad University
DOI https://doi.org/10.30486/mjee.2022.696500
Issue Vol. 16, No. 4 (2022)
Volume 16
The rapid increase in the number of medical image repositories nowadays has led to problems in managing and retrieving medical visual data. This has proved the necessity of Content-Based Image Retrieval (CBIR) with the aim of facilitating the investigation of such medical imagery. One of the most serious challenges that require special attention is the representational quality of the embeddings generated by the retrieval pipelines. These embeddings should include global and local features to obtain more useful information from the input data. To fill this gap, in this paper, we propose a CBIR framework that utilizes the power of deep neural networks to efficiently classify and fetch the most related medical images with respect to a query image. Our proposed model is based on combining Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) and learns to capture both the locality and also the globality of high-level feature maps. Our method is trained to encode the images in the database and outputs a ranking list containing the most similar image to the least similar one to the query. To conduct our experiments, an intermodal dataset containing ten classes with five different modalities is used to train and assess the proposed framework. The results show an average classification accuracy of 95.32 % and a mean average precision of 0.61. Our proposed framework can be very effective in retrieving multimodal medical images with the images of different organs in the body.
AN EARLY RNA-SEQ DETECTION SYSTEM FOR BREAST TUMOURS BASED ON MACHINE LEARNING
Apr 1, 2024Journal Journal of Engineering Science and Technology
Publisher School of Engineering, Taylor’s University
DOI https://jestec.taylors.edu.my/V19Issue2.htm
Issue Vol. 19, No. 2 (2024)
Volume 19
Cancer, a pervasive global health issue, accounts for approximately 9 million deaths annually. The survival rate of cancer patients significantly improves with early detection and accurate staging. In this context, ribonucleic acid sequencing (RNASeq) has become a powerful technique for measuring gene expression, thereby playing a crucial role in human disease research. On the other hand, there is a need for more efficient computational resources and tools for analysing RNA-Seq data. The RNA-Seq datasets known as the Cancer Genome Atlas (TCGA) were used in this research. In contrast, The following five types of cancer are included: Colon Adenocarcinoma, Prostate Adenocarcinoma, Renal Clear Cell Carcinoma, Lung Adenocarcinoma, and Breast Invasive Carcinoma. This research proposes a machine-learning technique based on the AdaBoost classifier for detecting, classifying, and predicting breast cancer. The findings of our proposed method exhibit remarkable performance, achieving a cross-validation accuracy of 99.77%,while the test and prediction accuracy were 100%. Critical parameters such as precision, recall, support, F1-score, and accuracy support this performance.
Secure routing protocol for wireless sensor networks: Survey
Jun 30, 2022Journal 2022 8th International Engineering Conference on Sustainable Technology and Development (IEC)
Publisher IEEE
DOI 10.1109/IEC54822.2022.9807582
Security is critical in Wireless Sensor Networks (WSNs) as they are utilized in various industries, including military, environmental monitoring, surveillance, and health care. Furthermore, it is considered a challenge for WSNs due to their limited resources, and deployments of the sensors in unattended and hostile filed have led to a growing demand for secure energy-effective protocols. Therefore, it needs to balance between security and energy consumption to keep the network's lifetime as long as possible with an acceptable level of security. Besides, the way of deploying the sensors in an unattended manner or hostile environment has led to the need for secure routing protocols to protect the transmission of data from the sensors to the base station. In this paper, we have outlined the network layer routing attacks on WSNs. This survey also discusses secure routing techniques for WSN and we have provided a comparison between existing secure routing protocols in terms of energy usage and the basic metric of security objective. Additionally, the latest strategies that are used by researchers in this field and the methods used to balance security and energy consumption were presented. Finally, the conclusion shows that most of the recent secure routing algorithms are not very effective due to various reasons like a huge amount of energy consumption, and large transmission overhead.
Transmission Control Protocol Global Synchronization Problem in Wide Area Monitoring and Control Systems
Feb 8, 2017Journal UHD Journal of Science and Technology
Publisher University of Human Development, Sulaimani, Kurdistan Region, Iraq.
DOI https://doi.org/10.21928/uhdjst.v1n2y2017.pp7-12
Issue Vol. 1 No. 2 (2017)
Volume 1
The electrical power network is a significant element of the critical infrastructure in modern society. Nowadays, wide area monitoring and control systems (WAMC) are becoming increasingly an important topic that motivates several researchers to improve, develop, and find the problems that hinder progress toward WAMC systems. WAMC is used to monitor and control the power network so the power network can be adapt to failures in automatic way. In this work, verification of the extent found a problem in transmission control protocol (TCP) which is called global synchronization and its impact on utilizing the buffer of the routers. A simulation models had been belt of WAMC system using OMNeT++ to study the performance of TCP in two queuing algorithms for measuring transmission of phasor measurement units and to test if global synchronization problem occurs. Three scenarios were used to test the survival of this problem on the system. It is found that the problem of global synchronization occurred in two scenarios which in turn causes low utilization for a buffer of routers.
A Review on Smart Cities Technologies, Challenges, and Solution
Apr 1, 2021Journal International Journal of Advances in Computer and Electronics Engineering
Issue 4
Volume 6
A great deal of considerable attention must be paid to smart cities to improve the quality of life and the efficiency of operations. At the same time, they can meet the future and current generations in terms of economic, social, environmental, and cultural aspects. The majority of people now live in cities, and the number of urban residents is expected to increase from 3.3 billion to 5 billion by 2030. The increasing population growth is the main motivation for work to transform cities into smart cities as the solution to address this increasing population. Later, technological development and the emergence of the Internet of Things led to the expansion of the concept of smart cities, and the work on them greatly by academics and industrialists alike. The main objective of this paper is to give the reader a fundamental understanding of smart cities, and then to give some introduction on the architecture of these cities from a network perspective. Also, we summarize and review the technologies and challenges of smart cities in general. This review is a reference for the general concept of smart cities and for authors who intend to work in this field