Comparative Analysis of DoS Attack Detection in KDD CUP99 using Machine Learning Classifier Algorithms

<abstract><p>In the realm of machine learning, where data-driven insights guide decision-making, addressing the challenges posed by class imbalance in datasets has emerged as a crucial concern. The effectiveness of classification algorithms hinges not only on their intrinsic capabilities but also on their adaptability to uneven class distributions, a common issue encountered across diverse domains. This study delves into the intricate interplay between varying class imbalance levels and the performance of ten distinct classification models, unravelling the critical impact of this imbalance on the landscape of predictive analytics. Results showed that random forest (RF) and decision tree (DT) models outperformed others, exhibiting robustness to class imbalance. Logistic regression (LR), stochastic gradient descent classifier (SGDC) and naïve Bayes (NB) models struggled with imbalanced datasets. Adaptive boosting (ADA), gradient boosting (GB), extreme gradient boosting (XGB), light gradient boosting machine (LGBM), and k-nearest neighbour (kNN) models improved with balanced data. Adaptive synthetic sampling (ADASYN) yielded more reliable predictions than the under-sampling (UNDER) technique. This study provides insights for practitioners and researchers dealing with imbalanced datasets, guiding model selection and data balancing techniques. RF and DT models demonstrate superior performance, while LR, SGDC and NB models have limitations. By leveraging the strengths of RF and DT models and addressing class imbalance, classification performance in imbalanced datasets can be enhanced. This study enriches credit risk modelling literature by revealing how class imbalance impacts default probability estimation. The research deepens our understanding of class imbalance's critical role in predictive analytics. Serving as a roadmap for practitioners and researchers dealing with imbalanced data, the findings guide model selection and data balancing strategies, enhancing classification performance despite class imbalance.</p></abstract>

Lung cancer is one of the three deadliest diseases in the world and has rapidly developed. Based on this, researchers conducted research to predict the factors that influence lung cancer. One method to identify this is using data mining methods and classification techniques. Researchers used several popular algorithms in classification to make comparisons of the most accurate algorithms for lung cancer classification. The algorithms used include K-Nearest Neighbor, Random Forest Classifier, Logistic Regression, Linear SVM, Naïve Bayes, Decision Tree, Random Forest, Gradient Boosting, Kernel SVM, and MLPClassifier. The researcher used this algorithm because, in the research that the researcher found on the Kaggle platform, he examined the comparison of the algorithm using the breast cancer dataset. In previous studies, their researchers used SVM, which obtained an accuracy of 96.47%, Neural Networks of 97.06%, and Naïve Bayes with an accuracy of 91.18% to study breast cancer. The difference from previous research is that this study uses several existing algorithms in Machine Learning such as K-Nearest Neighbor, Random Forest Classifier, Logistic Regression, Linear SVM, Naïve Bayes, Decision Tree, Random Forest, Gradient Boosting, Kernel SVM, and MLPClassifier. In addition, this research was conducted to see whether the results of the accuracy of the algorithm that the researchers carried out using the lung cancer dataset had different results. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood.

Research efforts in the prediction of stroke and diabetes prioritize early detection in order to enhance patient outcomes. To achieve this, a variety of methodologies are integrated. Existing studies, on the other hand, are marred by imbalanced datasets, lack of diversity in their datasets, potential bias, and inadequate model comparisons; these flaws underscore the necessity for more comprehensive and inclusive research methodologies. This paper provides a thorough assessment of machine learning algorithms in the context of early detection and diagnosis of stroke and diabetes. The research employed widely used algorithms, including Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors (KNN), and XGBoost Classifier, to examine medical data and derive significant findings. The XGBoost Classifier demonstrated superior performance, with an outstanding accuracy, precision, recall, and F1-score of 87.5%. The comparative examination of the algorithms indicated that the Decision Tree, Random Forest, and XGBoost classifiers consistently exhibited strong performance across all measures. The models demonstrated impressive discrimination capabilities, with the XGBoost Classifier and Random Forest reaching accuracy rates of roughly 87.5% and 86.5% respectively. The Decision Tree Classifier exhibited notable performance, with an accuracy rate of 83%. The overall accuracy of the models was evident in the F1-score, a metric that incorporates recall and precision, where the XGBoost model exhibited a marginal improvement of 2% over the Random Forest and Decision Tree models, and 4.25 percent over the last two. The aforementioned results underscore the effectiveness of the XGBoost Classifier, which will be employed as a predictive model in this study, alongside the Random Forest and Decision Tree models, for the accurate identification of stroke and diabetes. Furthermore, combining datasets improves model performance by utilizing relative features. This integrated dataset improves the model's efficiency and creates a resilient and comprehensive prediction model, improving healthcare outcomes. The findings of this research make a valuable contribution to the advancement of AI-driven diagnostic systems, hence enhancing the quality of healthcare decision-making.

This article investigates the problem of classifying network devices based on their security parameters using machine learning. Due to the constant growth of threats in cyberspace and the need to ensure a high level of network security, the relevance of using machine learning technologies to identify and classify secure devices is exceptionally high. Therefore, the article considers the specifics of applying machine learning algorithms for classification and regression tasks in network environments. Particular attention is paid to a short review of the algorithms most commonly used for classification tasks. The work describes in detail the process of developing a machine-learning model aimed at classifying network devices according to their security indicators. It considers the selection of appropriate parameters for model training, the process of data preprocessing, and the selection and adjustment of the classification algorithm. The results of model training on actual data are also presented. The process of training and evaluating the accuracy and efficiency of the model is described. The results are analyzed, and the choice of optimal hyperparameters is justified. As a result of the study, an effective machine learning model has been developed that can accurately classify network devices by security level, improving network security when selecting potentially secure devices. The study found that the Random Forest and Decision Tree models showed the highest accuracy in predicting the security state of network devices compared to other models, such as Logistic Regression, k-NN, and Gradient Boosting. The performance of the trained model was tested on a validation dataset. The Decision Tree model correctly predicted the security level of approximately 78% of network devices.

In the Internet of Things (IoT) technology, there are several issues to overcome, including network security. New attacks have been developed to target vulnerabilities in IoT devices, and the Internet of Things on a huge scale will exacerbate present network threats. Machine learning is becoming increasingly used in applications such as traffic classification and intrusion detection. This paper offers a technique for detecting network fault severity and identifying Internet of Things (IoT) devices based on several attributes. By pushing information to the network area, the proposed framework captures different features from each network flow in order to identify the source of traffic and the type of traffic generated is used to detect different network attacks. Different machine learning algorithms are tested to find the better suited algorithm that deliver best results. The following are some of the examples: Random Forest (RF) algorithm, decision tree, SVM, etc. After completing the experimentation, it was found that the random forest classifier and decision tree are the best performing ML algorithms to classify the network severity with an accuracy of about 96.98% and GNB is found as the least performing machine learning model with an accuracy of about 54.41%.

Cancer recurrences are poorly recorded within electronic health records around the world. This hinders research into the efficacy of cancer treatments. Currently, the retrospective identification of recurrence/progression diagnosis dates is achieved by staff who manually review patients' health records. This is expensive, time-consuming, and inefficient. Machine Learning models may expedite the review of health records and facilitate the assessment of alternative cancer therapies. This paper evaluates the use of four machine learning models (random forests, conditional inference trees, decision trees, and logistic regression) in identifying proxy dates of epithelial ovarian cancer recurrence/progression from chemotherapy data, in 531 patients at Leeds Teaching Hospital Trust. The random forest achieved the highest F1 score of 0.941 (95% confidence interval 0.916-0.968) when identifying recurrence events. Both the random forest and decision tree models' classifications closely conform to chart-reviewed time to next treatment, serving as a surrogate for recurrence-free survival. Additionally, all models reached an F1 score >0.940 when identifying patients whose cancer recurred/progressed. Our models proficiently identify both proxy dates for recurrence/progression diagnoses and patients whose cancer recurred/progressed. Considering the similar performance of the random forest and decision tree, model preference should be determined by the interpretability required to assist chart review and the ease of implementation into existing architecture.

A survey of trust computation models for service management in internet of things systems

There has been an overwhelming increase of connected Internet of Things (IoT) devices on the market in recent years, and the number is rapidly growing. The applications for IoT are nearly endless, and the emergence of house assistants made IoT available for the masses and everyday consumers. With this exponential growth come challenges, and one of the most pressing is perhaps the risk of privacy breach. These small IoT devices rarely have any real computing power, and therefore are rarely equipped with antivirus software or other safeguards. Most IoT devices rely on the same communication protocols that they have always used, and with the evolution of the internet of things, and the internet in general, there are revealed new vulnerabilities everyday due to little or no effort to update or patch the existing software in these devices. Even the companies that publish their device specifications and information, leave it almost impossible for the user to understand, or even find said information. With the Risk Assessment model, this research aims to give the users of smart devices a tool to determine the potential risks that are involved with the internet of things and the many different smart devices.KeywordsInternet of ThingsPrivacySmart household

Alzheimer's dementia, a neurological disease that affects millions of people worldwide, is a huge public health problem. It is critical to develop accurate prediction models since early detection can lead to more effective management and treatment. In this work, we investigate a range of hybrid machine-learning approaches that include Random Forest (RF) and Decision Tree (DT) as distinct models. Tree Forest Hybrid (TFH), TFH + Gradient Boosting (GB), Multi-Model Voting Ensemble (MVE), Multi Classifier Ensemble (MCE), and Naïve Bayes + GB are some of the models we investigate utilizing demographic and clinical features from the “oasis_longitudinal.csv” dataset. A comparison of the accuracy of numerous models indicates that four notable models, TFH MCE, MVE, and RF, each obtained an accuracy of 86.67%. NB + GB model with an accuracy of 85.33%, while the TFH+GB and DT models achieved an accuracy of 84%. Following a closer evaluation of these models' Root Mean Square Error (RMSE) and cross-validation scores, ‘TFH’ emerged as the highest performer, highlighting the promise of hybrid machine learning for improving Alzheimer's disease prediction.

Due to the rapid growth of the Internet of Things (IoT), researchers have demonstrated various IoT solutions, which are used to interconnect a wide range of IoT devices through the Internet. However, IoT stumbled into vertical silos; the available solutions provide specific IoT infrastructure, devices, protocols, data formats and models. This diversity and heterogeneity lead to interoperability issues. Heterogeneity happens at all IoT layers, especially at the application layer; devices often adopt mutually incompatible application-layer communication protocols to connect devices to IoT services. Furthermore, in order to integrate semantics to raw data, each system uses its one domain-specific ontology to make data more understandable and interpretable by adding semantic annotations. Working in isolation reduces the interoperability among IoT devices and systems, things across domains need to internetwork and collaborate to provide high level IoT services. Therefore, to alleviate the problem of both communication protocol interoperability and semantic interoperability across vertical silos of systems at the application layer, this paper proposes a semantic gateway (SGIoT) that acts as a bridge between heterogeneous sink nodes at the physical level and IoT services. SGIoT enables interconnectivity between communication protocols such as CoAP and MQTT regardless of their communication model, meanwhile it enables semantics integration throu gh cross-domain ontology (CDOnto) for semantic annotation, in order to provide interpretation of messages among IoT applications across domains. Our approach focuses on modularity and extensibility.

BackgroundEarly recurrence in colorectal cancer liver metastases (CRLM) typically correlates with significantly worse survival outcomes. There is a strong demand for developing robust and interpretable approaches to assist clinicians in identifying patients at high risk of recurrence.MethodsIn this study, we utilized clinical CT images and associated clinical data from 197 CRLM patients, provided as DICOM images. A total of 993 radiomic features, including shape, texture, and first-order characteristics, were extracted. Eight machine learning models were trained and validated: Random Forest (RF), Multilayer Perceptron (MLP), K-nearest Neighbors (KNN), Extremely Randomized Trees (ET), AdaBoost, Decision Trees (DT), Gradient Boosting (GB), and Linear Discriminant Analysis (LDA).ResultsIn predicting tumor recurrence within one year, the ET model showed the best performance using only radiomic features, with an AUC of 0.9667. RF and GB also performed well, achieving AUCs of 0.9558 and 0.9227, respectively. When combining radiomic and clinical features, the performance of all models improved in terms of AUC. Specifically, the Random Forest (RF) model achieved the highest AUC of 0.9672, followed by Gradient Boosting (GB) with an AUC of 0.9646, and Extra Trees (ET) with an AUC of 0.9459.ConclusionWe developed a CT-based machine learning model, using the Random Forest algorithm, that combines clinical (e.g., age, carcinoembryonic antigen, bilobar disease) and radiomic features (e.g., selected features included texture-based metrics such as the 90th percentile of first-order statistics in the high–low–low (HLL) wavelet-decomposed image, and Run Entropy from the gray-level run length matrix (GLRLM) in the low–low–low (LLL) sub-band.) to predict early recurrence after hepatectomy in patients with colorectal liver metastasis (CRLM). This model has the potential to guide personalized postoperative surveillance. However, limitations such as the retrospective single-center design and relatively small sample size may affect the generalizability of the findings. Further validation in larger, multi-center cohorts is warranted to confirm its clinical utility.

Accurate forecasting of greenhouse gas (GHG) emissions is essential for assessing climate change dynamics and developing evidence-based environmental policies. This study aims to comparatively evaluate the prediction performance of various machine learning algorithms using annual GHG emission data (CO2, CH4, and N2O) for Turkey from 2012 to 2021. The dataset was split into 80% training and 20% testing subsets. The input variables consist of the year and emission category codes, while the output variable represents the annual emission value for each gas. The machine learning algorithms applied in the analysis include random forest, decision tree, ensemble regressor, LightGBM, gradient boosting, and XGBoost. Model performance was assessed using error metrics such as R2, MAE, RMSE, and MSE. The results indicate that gradient boosting algorithms particularly gradient boosting (R2 = 0.995) and XGBoost (R2 = 0.994) achieved the highest accuracy, significantly outperforming other models. LightGBM and ensemble regressor also delivered strong predictive performance, whereas the decision tree model showed the lowest accuracy. The analysis further reveals that more than 90% of total GHG emissions are attributable to CO2, and all three gases exhibited a consistent upward trend over the study period. This study is among the few to focus on the annual level forecasting of greenhouse gas emissions in Turkey using machine learning algorithms. It offers a comparative evaluation of random forest and gradient boosting methods, highlighting their performance across different emission categories. The study contributes to data-driven decision-making processes in regional climate policy. Furthermore, the findings suggest that integrating AI-based forecasting tools into GHG monitoring systems can significantly enhance transparency, accuracy, and response capacity in climate governance.

FakeNews is one of the most popular phenomena that have considerable effects on our social life, especially in the political domain. Nowadays, creating fake news becomes very easy because of users' widespread using the internet and social media. Therefore, the detection of elusiveness news is a crucial problem that needs to be considerable mainly because of its challenges like the limited amount of the benchmark datasets and the amount of the published news every second. This research proposed utilizing two different machine learning algorithms (random forest and decision tree (J48)) to detect the fake news. In this paper, the full dataset size equals 20,761 samples, while the testing sample size equals 4,345 samples.The preprocessing steps start with cleaning data by removing unnecessary special characters, numbers, English letters, and white spaces, and finally, removing stop words is implemented. After that, the most popular feature extraction method (TF-IDF) is used before applying the two suggested classification algorithms. The results show that the best accuracy achieved equals 89.11% using the decision tree model while using the random forest; the accuracy achieved equals 84.97 %.

ObjectiveTo evaluate the diagnostic and prognostic predictive value of the pan-immune-inflammation value (PIV) and triglyceride-glucose (TyG) index in premature coronary artery disease (PCAD).MethodsThis study analyzed data from 26,883 patients admitted with chest pain at Liuzhou People's Hospital (January 2014 to December 2020), with 5,653 patients included after screening. Multiple machine learning algorithms, including Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Lasso regression, Random Forest (RF), and logistic regression, were applied to identify PCAD-related variables, which were integrated into a decision tree model. Propensity score matching (PSM) ensured cohort comparability. The Mime1 package facilitated ensemble feature selection and visualization, while optimal PIV and TyG cutoff values were determined via Receiver Operating Characteristic (ROC) analysis for 36-month survival subgroup analysis.ResultsLogistic regression identified PIV [odds ratio [OR] 2.651, 95% CI [to be specified], P < 0.001] and TyG [OR 1.003, 95% CI (to be specified), P < 0.001] as PCAD risk factors. The decision tree model, incorporating PIV, TyG, and white blood cell count (WBC), achieved an accuracy of 0.88 and an area under the ROC curve (AUC) of 0.86 for PCAD diagnosis. Survival analysis over 36 months revealed that low PIV and TyG levels were associated with reduced all-cause mortality, whereas elevated levels correlated with poorer prognosis (P < 0.001), with TyG showing a pronounced effect.ConclusionThe combined evaluation of PIV, TyG, and WBC offers robust diagnostic and prognostic value for PCAD, with elevated PIV and TyG levels indicating a poor prognosis, underscoring their potential as clinical biomarkers.

Asymmetric cryptography algorithms, still considered the most robust tool available in the cryptography domain. It incorporates intensive modular exponentiation calculations, which entail considerable computing power, memory and storage space. Common IoT device is equipped with limited computing resources and so, for security purposes, it can execute symmetric and limited asymmetric cryptography. In most cases, IoT devices do not have the capacity required for executing massive modular multiplications of numbers of magnitude of 4 K bits and more. This leads to the lack of asymmetric cryptography in the IoT domain resulting with a reduction in security means to cope with the raising security challenges. The security problem increases as the number of IoT devices is expected to significantly grow soon. We propose a new implementation of asymmetric cryptography, which splits its heavy calculations into micro-processes, where each micro-process is distributed to an appropriate IoT device, connected to the network. The accepted result is transferred back to the distributing IoT. Once all the results are accumulated, a consolidation process is activated to generate the final calculation result, which then is fed into the cryptography process, to generate the Encrypted/Decrypted string, proving the ability to maintain asymmetric cryptography also at the IoT level without compromising security.