The ever-evolving landscape of cyber threats necessitates robust and adaptable intrusion detection systems (IDS) capable of identifying both known and emerging attacks. Traditional IDS models often struggle with detecting novel threats, leading to significant security vulnerabilities. This paper proposes an optimized intrusion detection model using Support Vector Machine (SVM) algorithms tailored to detect known and innovative cyberattacks with high accuracy and efficiency. The model integrates feature selection and dimensionality reduction techniques to enhance detection performance while reducing computational overhead. By leveraging (...) advanced optimization techniques such as Grid Search and Particle Swarm Optimization (PSO), the proposed SVM-based IDS achieves superior classification results. (shrink)

The ever-evolving landscape of cyber threats necessitates robust and adaptable intrusion detection systems (IDS) capable of identifying both known and emerging attacks. Traditional IDS models often struggle with detecting novel threats, leading to significant security vulnerabilities. This paper proposes an optimized intrusion detection model using Support Vector Machine (SVM) algorithms tailored to detect known and innovative cyberattacks with high accuracy and efficiency. The model integrates feature selection and dimensionality reduction techniques to enhance detection performance while reducing computational overhead.

Detecting fraud in financial transactions is crucial for guaranteeing the integrity and security of financial systems. This paper presents an integrated approach for detecting fraudulent activities that incorporates Support Vector Machines (SVM) and Feedforward Neural Networks (FFNN). The proposed methodology utilizes the strengths of SVM and FFNN to distinguish between classes and capture complex patterns and relationships, respectively. The SVM model functions as a feature extractor, supplying the FFNN with high-level representations as inputs. Through an exhaustive evaluation utilizing labeled financial (...) transaction data, the integrated SVM-FFNN model shows promise in detecting fraud with increased accuracy and precision. This research contributes to the development of innovative techniques for enhancing financial fraud detection systems. (shrink)

Nowadays, intrusions have become a major problem faced by users. To stop these cyber attacks from happening, the development of a reliable and effective Intrusion Detection System (IDS) for cyber security has become an urgent issue to be solved. The proposed IDS model is aimed at detecting network intrusions by classifying all the packet traffic in the network as benign or malicious classes. The Canadian Institute for Cyber security Intrusion Detection System (CICIDS2017) dataset has been used to train and validate (...) the proposed model. The model has been evaluated in terms of the overall accuracy, attack detection rate, false alarm rate, and training overhead. DDOS attacks based on Canadian Institute for Cyber security Intrusion Detection System (KDD Cup 99) dataset has been used to train and validate. For validation, comparison for 2 dataset (CICIDS2017 and KDD Cup 99) is done. (shrink)

The ever-evolving landscape of cyber threats necessitates robust and adaptable intrusion detection systems (IDS) capable of identifying both known and emerging attacks. Traditional IDS models often struggle with detecting novel threats, leading to significant security vulnerabilities. This paper proposes an optimized intrusion detection model using Support Vector Machine (SVM) algorithms tailored to detect known and innovative cyberattacks with high accuracy and efficiency. The model integrates feature selection and dimensionality reduction techniques to enhance detection performance while reducing computational overhead. By leveraging (...) advanced optimization techniques such as Grid Search and Particle Swarm Optimization (PSO), the proposed SVM-based IDS achieves superior classification results. (shrink)

The college hopes that every semester students are able to pay tuition properly and smoothly. The hope is that the institution will be able to maintain monthly cash flow so that its operational and maintenance costs can be met. Therefore, this study was conducted to predict and fulfill the institution's cash-in from the method of paying tuition fees either by cash, installments, or sometimes late payments every semester. In predicting the method of paying tuition fees, using student profile data (name, (...) name, study program) and achievement index every semester for 5 semesters passed and the method of payment (cash, installments, and late--cash or installments). Using the Naive Bayes (NB) method, Support Vector Machine (SVM), and Deep Learning, this study aims to forecast tuition costs. The Classification Prediction Model with Naive Bayes, SVM, and Deep Learning produces Confusion Matrix Performance NB with an Accuracy of 91.49%, Confusion Matrix Performance SVM with an Accuracy of 85.11%, and Confusion Matrix Performance Deep Learning with an Accuracy of 89.36%, according to the research findings. (shrink)

Nowadays, intrusions have become a major problem faced by users. To stop these cyber attacks from happening, the development of a reliable and effective Intrusion Detection System (IDS) for cyber security has become an urgent issue to be solved. The proposed IDS model is aimed at detecting network intrusions by classifying all the packet traffic in the network as benign or malicious classes. The Canadian Institute for Cyber security Intrusion Detection System (CICIDS2017) dataset has been used to train and validate (...) the proposed model. The model has been evaluated in terms of the overall accuracy, attack detection rate, false alarm rate, and training overhead. DDOS attacks based on Canadian Institute for Cyber security Intrusion Detection System (KDD Cup 99) dataset has been used to train and validate. For validation, comparison for 2 dataset (CICIDS2017 and KDD Cup 99) is done. Then, to implement the Deep learning algorithms is proposed. Method Classification using SVM algorithm Model predict is done. Testing dataset for anomaly detection model classified as attack or normal. Finally, the experimental results shows that the performance metrics such as accuracy, precision, recall and confusion matrix. (shrink)

The crop recommendation system employing machine learning methods will be covered in this study. For sustainable agricultural practices to be followed and to increase crop yields, crop advice is crucial. Based on several factors, including nitrogen (N), phosphorus (P), potassium (K), and humidity, we will advise the best crop for the given site. We analyzed various algorithms like KNN, Decision Tree, Random Forest, SVM etc. But based on various accuracy levels we committed to random forest implementation. Means in this paper (...) we are going to implement a crop recommendation system using random forest algorithm. The model is allowed to train upon a large dataset and the Performance of the recommendation system is measured using accuracy score. Finally, Using the trained model we are going to predict suitable crops for land according to the given parameters. Our proposed approach can be helpful for farmers, researchers, and policymakers in making informed decisions regarding crop management and planning. -/- . (shrink)

As Distributed Denial of Service (DDoS) attacks evolve, accurately detecting these threats becomes essential to ensuring network stability. Traditional methods often face challenges in recognizing adaptive DDoS patterns and balancing detection accuracy with false positives. This paper presents a machine learning-based framework leveraging Gaussian Naive Bayes, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and an Ensemble Random Forest classifier. Through an in-depth performance analysis using accuracy and AUC-ROC metrics, the hybrid model aims to provide a robust, scalable solution to enhance (...) network security. (shrink)

Breast cancer is one of the leading causes of death among women worldwide. Early detection plays a crucial role in improving survival rates, and machine learning (ML) provides powerful tools for identifying cancerous tumors in medical imaging and diagnostic data. This paper explores various machine learning techniques used for breast cancer detection, with a particular focus on the Wisconsin Breast Cancer Dataset (WBCD). We evaluate several classification models, including Logistic Regression (LR), Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Random (...) Forest (RF), for their ability to accurately classify benign and malignant tumors. The goal of this paper is to demonstrate the use of supervised learning techniques to enhance early breast cancer detection. (shrink)

Speech Emotion Detection (SED) refers to the identification of human emotions based on speech signals. The goal of this research is to design and implement a system that can accurately classify emotions from speech using machine learning techniques. The system can be applied in various fields such as healthcare, customer service, human-computer interaction, and mental health monitoring. The paper discusses the various stages of building such a system, from collecting and preprocessing audio data to selecting machine learning models and evaluating (...) the performance of the system. A combination of feature extraction techniques and machine learning algorithms, such as Support Vector Machines (SVM) and deep learning models like Long Short-Term Memory (LSTM) networks, is employed to achieve high accuracy. (shrink)

The proposed IDS model is aimed at detecting network intrusions by classifying all the packet traffic in the network as benign or malicious classes. The Canadian Institute for Cyber security Intrusion Detection System (CICIDS2017) dataset has been used to train and validate the proposed model. The model has been evaluated in terms of the overall accuracy, attack detection rate, false alarm rate, and training overhead. DDOS attacks based on Canadian Institute for Cyber security Intrusion Detection System (KDD Cup 99) dataset (...) has been used to train and validate. For validation, comparison for 2 dataset (CICIDS2017 and KDD Cup 99) is done. Then, to implement the Deep learning algorithms is proposed. Method Classification using SVM algorithm Model predict is done. (shrink)

This paper presents a machine learning-based framework for real-time short-term snowfall forecasting by integrating atmospheric and topographic data. The model uses real-time meteorological data such as temperature, humidity, and pressure, along with terrain data like elevation and land cover, to predict snowfall occurrence within a 12-hour forecast window. Random Forest (RF) and Support Vector Machine (SVM) models are employed to process these multi-source inputs, demonstrating a significant improvement in prediction accuracy over traditional methods. Experimental results show that the RF model (...) achieved a root mean square error (RMSE) of 3.2 cm, while traditional regression models achieved an RMSE of 5.1 cm. The proposed framework provides a more reliable and accurate tool for real-time snowfall prediction, especially in mountainous regions, and can be deployed for operational weather forecasting applications. (shrink)

Impostor syndrome or Impostor phenomenon is a belief that a person thinks their success is due to luck or external factors, not their abilities. This psychological trait is present in certain groups like women. In this paper, we propose a neutrosophic trait measure to represent the psychological concept of the trait-anti trait using refined neutrosophic sets. This study analysed a group of 200 undergraduate students for impostor syndrome, perfectionism, introversion and self-esteem: after the COVID pandemic break in 2021. Data labelling (...) was carried out using these neutrosophic trait measures. Machine learning models like Support Vector Machine(SVM), K-nearest neighbour (K-NN), and random forest were used to model the data; SVM provided the best accuracy of 92.15%. (shrink)

With the increasing popularity of social networking websites, the problem of fake profiles has become a significant concern. Fake profiles, often created by malicious actors for fraudulent purposes, pose threats to user privacy, security, and trustworthiness of online platforms. This project proposes a machine learning-based approach to detect fake profiles on social networking websites. By analyzing various features such as user activity patterns, profile attributes, and network connections, the model identifies potential fake profiles with high accuracy. The system employs a (...) variety of machine learning algorithms, including decision trees, support vector machines (SVM), and random forests, to classify profiles as either genuine or fake. Data preprocessing techniques such as feature extraction, normalization, and outlier detection are applied to enhance the model's performance. The proposed approach is evaluated on a dataset of social network profiles, and its effectiveness is compared to existing methods in terms of precision, recall, and F1-score. The results demonstrate the ability of the machine learning model to detect fake profiles accurately, providing a valuable tool for social networking platforms to protect users from potential threats and improve the overall user experience. This solution can also help in the automated detection of fraudsters and reduce the manual effort required for profile validation. (shrink)

SMS spam has become a widespread issue, leading to significant inconvenience and security risks for users. Detecting and filtering out such spam messages is crucial for enhancing the user experience and ensuring privacy. TThe dataset used for training and testing the model consists of labeled SMS messages, which are processed using feature extraction techniques such as TF-IDF and word tokenization. Several machine learning algorithms, including Naive Bayes, Support Vector Machine (SVM), and Random Forest, are evaluated to determine the best-performing model (...) for spam detection. The system is trained and tested using a variety of performance metrics, including accuracy, precision, recall, and F1-score. The results show that machine learning models, particularly Naive Bayes, exhibit high accuracy in distinguishing spam from legitimate messages. This system can be implemented in real-time applications such as mobile phones and email services to improve spam detection and reduce unwanted content. By automating the spam filtering process, the system enhances the efficiency and reliability of communication systems. (shrink)

This research project utilized advanced computer algorithms to predict the outcomes of Premier League soccer matches. The dataset containing match data and odds from seasons was processed to handle missing information, select features and reduce complexity using Principal Component Analysis. To address imbalances, in the target variable Synthetic Minority Over sampling Technique (SMOTE) was employed. Various machine learning models such as RandomForest, DecisionTree, SVM, XGBoost and LightGBM were evaluated.

The project titled "Efficient Machine Learning Algorithm for Future Gold Price Prediction" focuses on the development of a machine learning model that can accurately predict future gold prices using historical data and various economic indicators. Gold has long been regarded as a safe-haven asset, and its price is influenced by multiple factors, including global economic conditions, inflation rates, interest rates, and geopolitical events. This research aims to design and implement a robust machine learning model that can analyze complex patterns and (...) trends in gold prices to generate reliable predictions. The project employs a range of machine learning techniques such as Linear Regression, Random Forest, and Support Vector Machines (SVM) to build the prediction model. It utilizes key features like historical price data, currency exchange rates, commodity prices, and stock market trends as input variables. The performance of the model is evaluated using standard metrics such as accuracy, precision, recall, and RMSE (Root Mean Squared Error). The final model is optimized for accuracy and efficiency, making it a useful tool for investors and financial analysts who seek to forecast gold prices and make informed investment decisions. (shrink)

Heart disease remains one of the leading causes of mortality worldwide. Early prediction and diagnosis are critical in preventing severe outcomes and improving the quality of life for patients. This project focuses on developing a robust heart disease prediction system using machine learning techniques. By analyzing a comprehensive dataset consisting of various patient attributes such as age, sex, blood pressure, cholesterol levels, and other medical parameters, the system aims to predict the likelihood of a patient having heart disease. The project (...) employs various machine learning algorithms such as Logistic Regression, Decision Trees, Support Vector Machines (SVM), and Random Forests to classify the data and provide an accurate prediction. The system's performance is evaluated using metrics like accuracy, precision, recall, and F1-score, ensuring that it can offer reliable results in real-world applications. Furthermore, feature selection techniques are applied to identify the most significant factors contributing to heart disease, thus improving the model's interpretability. The proposed solution is intended to aid healthcare professionals by providing early alerts and recommendations, ultimately facilitating timely interventions. (shrink)

Chronic Kidney Disease (CKD) is a significant global health issue, often leading to kidney failure and requiring costly medical treatments such as dialysis or transplants. Early detection of CKD is essential for timely intervention and improved patient outcomes. This project aims to develop a machine learning-based predictive model for diagnosing CKD at an early stage. By utilizing a range of clinical features such as age, blood pressure, blood sugar, and other relevant biomarkers, we employ machine learning algorithms, including Decision Trees, (...) Random Forests, and Support Vector Machines (SVM), to predict the likelihood of a patient developing CKD. The dataset used in this study includes medical records of patients with various kidney conditions, and preprocessing techniques such as normalization and missing data handling are applied to ensure the model’s robustness. The performance of the model is evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure reliable predictions. (shrink)

This project aims to develop a machine learning-based predictive model for diagnosing CKD at an early stage. By utilizing a range of clinical features such as age, blood pressure, blood sugar, and other relevant biomarkers, we employ machine learning algorithms, including Decision Trees, Random Forests, and Support Vector Machines (SVM), to predict the likelihood of a patient developing CKD. The dataset used in this study includes medical records of patients with various kidney conditions, and preprocessing techniques such as normalization and (...) missing data handling are applied to ensure the model’s robustness. The performance of the model is evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure reliable predictions. (shrink)

Research in ethical AI has made strides in quantitative expression of ethical values such as fairness, transparency, and privacy. Here we contribute to this effort by proposing a new family of metrics called “decisional value scores” (DVS). DVSs are scores assigned to a system based on whether the decisions it makes meet or fail to meet a particular standard (either individually, in total, or as a ratio or average over decisions made). Advantages of DVS include greater discrimination capacity between types (...) of ethically relevant decisions and facilitation of ethical comparisons between decisions and decision-making systems, including across different modalities (for instance: human, machine, or coupled human–machine systems). After clarifying ambiguities in the concept of “decision” itself, including the question of how to individuate the decisions made by a system, we discuss the role and meaning of “decision” in common AI and machine learning approaches such as decision trees, neural networks, SVMs, and unsupervised classifiers. We then show how DVSs may be defined for several ethical values of interest, with an extended discussion of transparency. Finally, we explore how such metrics can be applied to real decision-making systems through two case studies: evaluations of LLMs for transparency; and evaluations of criminal risk assessment tools for utility, rights violations, fairness, and transparency. (shrink)

Due to the development of advanced identity based attacks and even complex cyber threats, merely possessing defensive cyber security capabilities is not enough today. In this study, we investigate how predictive analytics based machine learning (ML) can be employed for pro-active identity management and threat detection. In this study, the authors assess some models of machine learning – Decision Trees, Random Forests, Support Vector Machines (SVM), and a new hybrid one – to determine which best allows for the detection of (...) both known and unknown threats. The results reveal that in metrics such as accuracy, precision, recall, and F1 score. The hybrid model incorporating both supervised and unsupervised learning approaches scored the highest among other models. As a consequence of its adaptability, the hybrid model is capable of real time dynamic threat detection and anomaly based identity management which makes it an appropriate model for the changing cyber security environment. This study provides the prospects to make proactive cybersecurity more efficient and therefore enhancing the technology for protection systems. (shrink)

This project aims to develop a predictive system capable of identifying crime types and predicting their occurrences based on historical crime data. The system uses advanced machine learning techniques to analyze factors such as geographic location, time, and other socio-economic variables, enabling authorities to better understand crime patterns and trends. By training models on vast datasets of past criminal activities, the system predicts not only the likely occurrence of specific crime types but also identifies high-risk locations and times, empowering law (...) enforcement to allocate resources more effectively and proactively prevent crime. Various machine learning algorithms, including Decision Trees, Random Forests, and Support Vector Machines (SVM), are employed to ensure accuracy and robustness. The system's predictions can significantly enhance crime management and law enforcement strategies by offering insights into crime prevention and mitigation efforts. This approach facilitates informed decision-making and fosters safer communities by providing accurate forecasts based on data-driven insights. The project underscores the potential of machine learning in public safety and law enforcement, transforming crime prediction and management from reactive to proactive. (shrink)

Due to the development of advanced identity based attacks and even complex cyber threats, merely possessing defensive cyber security capabilities is not enough today. In this study, we investigate how predictive analytics based machine learning (ML) can be employed for pro-active identity management and threat detection. In this study, the authors assess some models of machine learning – Decision Trees, Random Forests, Support Vector Machines (SVM), and a new hybrid one – to determine which best allows for the detection of (...) both known and unknown threats. The results reveal that in metrics such as accuracy, precision, recall, and F1 score. The hybrid model incorporating both supervised and unsupervised learning approaches scored the highest among other models. As a consequence of its adaptability, the hybrid model is capable of real time dynamic threat detection and anomaly based identity management which makes it an appropriate model for the changing cyber security environment. This study provides the prospects to make proactive cybersecurity more efficient and therefore enhancing the technology for protection systems. (shrink)

: COVID-19 has proliferated over the earth, exposing mankind at risk. The assets of the world's most powerful economies are at stake due to the disease's high infectivity and contagiousness. The capacity of machine learning algorithms can estimate the amount of future COVID-19 cases, which is now considered a possible threat to civilization. Five conventional measuring models, notably LR, LASSO, SVM, ES, and LSTM, were utilised in this work to examine COVID-19's undermining variables. Each model contains three sorts of expectations: (...) the number of newly contaminated cases, the number of passings, and the number of recoveries. However, it is hard to anticipate the patients' real outcomes. To address the issue, a suggested approach based on long transient memory (LSTM) forecasts the number of COVID-19 cases in the next 10 days as well as the impact of preventative measures such as social isolation and lockdown on COVID-19 spread. (shrink)

Objective: To evaluate the potential of arterial spin labeling (ASL) as an alternative to FDG-PET in the diagnosis of disorders of consciousness (DOC), we conducted a comparative study of the two modalities. Methods: A total of 36 DOC patients (11 female; mean age = 49.67 ± 14.54 years) and 17 healthy control (HC) participants (9 female; mean age = 31.9 ± 9.6 years) underwent both FDG-PET scans that measure metabolism via glucose uptake and ASL scans that measure cerebral blood flow (...) (CBF). CBF and metabolism in DOC and HC were compared, globally and for seven functional networks. Comparability of the two modalities was estimated using Spearman partial correlation for both global and network levels. Furthermore, a support vector machine (SVM) algorithm was used to train two classifiers to distinguish DOC patients from HC with normalized CBF or metabolism values from the seven networks. Performance of these classifiers was first evaluated through leave-one-subject-out (LOSO) cross-validation within their respective modalities. Subsequently, cross-modal validation was conducted: testing the ASL-trained classifier with PET data (ASL-to-PET validation) and vice versa (PET-to-ASL validation). Performance of each classifier was assessed using receiver operating characteristic (ROC) analysis, with area under the curve (AUC) as the metric. Results: Both modalities showed agreement in decreased CBF and metabolism in DOC patients compared to HC, at both global and network levels. The global brain and most networks showed significant positive partial correlation between CBF and metabolism. SVM classifiers, utilizing activity from seven networks as features, performed well in the both LOSO cross-validation (ASL-trained classifier: accuracy = 83.02%, AUC = 0.95; PET-trained classifier: accuracy = 98.12%, AUC = 0.98) and cross-modal validation (ASL-to-PET validation: accuracy = 84.90%, AUC =0.92; PET-to-ASL validation: accuracy = 73.58%, AUC = 0.93). Conclusion: Our results demonstrate that ASL provides information comparable to FDG-PET for DOC patients; moreover, classifiers trained on ASL data perform comparably well to those trained on FDG-PET data. Therefore, ASL could be a valuable alternative to FDG-PET in the clinical diagnosis of DOC, especially in light of its advantages: ease of acquisition, avoidance of radiation exposure, brevity of scanning time, and lower-cost. (shrink)

Customer churn prediction is a critical challenge for businesses in retaining their customer base and optimizing their marketing strategies. Machine learning (ML) techniques offer a powerful approach to predict customer churn by analyzing historical customer behavior, demographic information, and usage patterns. This paper provides an overview of machine learning-based models used for predicting customer churn, including classification algorithms such as logistic regression, decision trees, random forests, support vector machines (SVM), and neural networks. We explore how businesses can leverage these models (...) to identify customers who are likely to churn and take proactive measures to retain them. The paper also highlights the challenges in churn prediction, such as imbalanced data, overfitting, and the interpretability of models, and provides insights into the future of churn prediction models. Case studies in telecommunications, retail, and banking sectors are discussed to demonstrate practical applications. (shrink)

Emotion recognition from speech is an important aspect of human-computer interaction (HCI) systems, allowing machines to better understand human emotions and respond accordingly. This paper explores the use of machine learning techniques to recognize emotions in speech signals. We leverage the librosa library for feature extraction from audio files and train multiple machine learning models, including Support Vector Machine (SVM), Random Forest (RF), and k-Nearest Neighbors (k-NN), to classify speech emotions. The aim is to create an automated system capable of (...) identifying emotions like happy, sad, angry, neutral, and surprised from speech audio. (shrink)

Chronic Kidney Disease (CKD) is a significant global health issue, often leading to kidney failure and requiring costly medical treatments such as dialysis or transplants. Early detection of CKD is essential for timely intervention and improved patient outcomes. This project aims to develop a machine learning-based predictive model for diagnosing CKD at an early stage. By utilizing a range of clinical features such as age, blood pressure, blood sugar, and other relevant biomarkers, we employ machine learning algorithms, including Decision Trees, (...) Random Forests, and Support Vector Machines (SVM), to predict the likelihood of a patient developing CKD. (shrink)

Chronic Kidney Disease (CKD) is a significant global health issue, often leading to kidney failure and requiring costly medical treatments such as dialysis or transplants. Early detection of CKD is essential for timely intervention and improved patient outcomes. This project aims to develop a machine learning-based predictive model for diagnosing CKD at an early stage. By utilizing a range of clinical features such as age, blood pressure, blood sugar, and other relevant biomarkers, we employ machine learning algorithms, including Decision Trees, (...) Random Forests, and Support Vector Machines (SVM), to predict the likelihood of a patient developing CKD. The dataset used in this study includes medical records of patients with various kidney conditions, and preprocessing techniques such as normalization and missing data handling are applied to ensure the model’s robustness. The performance of the model is evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure reliable predictions. This approach not only aims to improve diagnostic accuracy but also provides a data-driven solution to assist healthcare professionals in making informed decisions. The outcome of this project can contribute to better management of CKD, ultimately helping to reduce the burden on healthcare systems and improving patient care. (shrink)

Chronic Kidney Disease (CKD) is a significant global health issue, often leading to kidney failure and requiring costly medical treatments such as dialysis or transplants. Early detection of CKD is essential for timely intervention and improved patient outcomes. This project aims to develop a machine learning-based predictive model for diagnosing CKD at an early stage. By utilizing a range of clinical features such as age, blood pressure, blood sugar, and other relevant biomarkers, we employ machine learning algorithms, including Decision Trees, (...) Random Forests, and Support Vector Machines (SVM), to predict the likelihood of a patient developing CKD. The dataset used in this study includes medical records of patients with various kidney conditions, and preprocessing techniques such as normalization and missing data handling are applied to ensure the model’s robustness. The performance of the model is evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure reliable predictions. This approach not only aims to improve diagnostic accuracy but also provides a data-driven solution to assist healthcare professionals in making informed decisions. The outcome of this project can contribute to better management of CKD, ultimately helping to reduce the burden on healthcare systems and improving patient care. (shrink)

Text classification is one of the most important task in natural language processing, In this research, we carried out several experimental research on three (3) of the most popular Text classification NLP classifier in Convolutional Neural Network (CNN), Multinomial Naive Bayes (MNB), and Support Vector Machine (SVN). In the presence of enough training data, Deep Learning CNN work best in all parameters for evaluation with 77% accuracy, followed by SVM with accuracy of 76%, and multinomial Bayes with least performance of (...) 69% accuracy. CNN has the best performance in the presence of large enough training dataset because of the presence of filter/ kernels which help to indentify patterns in text data regardless of their position in the sentence. We repeated the training again with just one-third of our data, at this point SVM comes with the best performance, the performance of CNN noticeably drops but still better than Multinomial Naive Bayes, the reason why SVM works best when we reduce the training data was because of its ability to look for a hyper-plane that creates a boundary between different classes of data so as to properly classify them, so we believed that getting the hyper-plane was more efficient when we reduce the dataset, hence reason for the good performance. Multinomial Naive Bayes have the least performance which we attributed to its assumption of independency between the features which sometimes does not hold true. We concluded that availability of data should be an important factor when choosing classifier for Natural Language Processing Text Classification task. CNN should be use in the presence of enough dataset, and SVM should be use when data is not enough. Multinomial Naive Bayes must not be trusted with state of the art NLP task due to its assumption of independency between the features . (shrink)

The advancement of machine learning (ML) has revolutionized healthcare by enabling the early detection and diagnosis of multiple diseases. This paper presents a Multiple Disease Prediction System using machine learning algorithms to analyze patient data and predict the likelihood of diseases such as diabetes, heart disease, and kidney disease. The proposed model utilizes various ML classifiers, including Decision Trees, Random Forest, Support Vector Machines (SVM), and Neural Networks, to enhance prediction accuracy. The system aims to provide a costeffective, accurate, and (...) efficient tool for healthcare professionals and patients. (shrink)

With the growing sophistication and frequency of cyberattacks, there is a critical need for effective systems that can detect and prevent breaches in real time. The AI/ML-based Network Intrusion Detection System (NIDS) addresses this need by analyzing traffic patterns to identify security breaches in firewalls, routers, and network infrastructures. By integrating machine learning algorithms—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest—the system is able to detect both known cyber threats and previously unseen attack vectors. Unlike traditional methods that (...) rely heavily on predefined indicators of compromise (IoCs), this system utilizes anomaly detection techniques, allowing it to identify new and emerging threats. As cyberattacks evolve, organizations must adopt adaptive methods to secure their networks. This system achieves high accuracy in classifying network traffic, with real-time alerts that provide early warnings of suspicious activities. It also includes intuitive visualizations, helping network administrators gain insights into the nature and scope of attacks. With the rise of increasingly complex and frequent cyberattacks, this NIDS offers a robust solution for enhancing network security and response capabilities. (shrink)

Facial recognition is a computer vision task that involves identifying or verifying individuals based on their facial features. It has widespread applications in security, authentication, and human-computer interaction. Supervised learning techniques have become the foundation for facial recognition systems, as they enable the model to learn from labeled data to recognize patterns and make predictions. This paper explores the use of supervised learning algorithms, such as Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and k-Nearest Neighbors (k-NN), for facial recognition (...) tasks. We will demonstrate how these algorithms can be used to accurately identify individuals by learning from training datasets with labeled facial images. (shrink)

By utilizing a range of clinical features such as age, blood pressure, blood sugar, and other relevant biomarkers, we employ machine learning algorithms, including Decision Trees, Random Forests, and Support Vector Machines (SVM), to predict the likelihood of a patient developing CKD. The dataset used in this study includes medical records of patients with various kidney conditions, and preprocessing techniques such as normalization and missing data handling are applied to ensure the model’s robustness. T.

The main aim of this project is to detect fraudulent credit card transactions by utilizing credit card details. As financial transactions grow in volume and complexity, it becomes increasingly critical for credit card companies to identify fraudulent activities to protect customers from unauthorized charges. Although instances of fraud are relatively infrequent, they present substantial financial risks to both consumers and financial institutions. This research employs three machine learning techniques—One-Class SVM, Local Outlier Factor, and Isolation Forest—to analyse transaction data in real-time, (...) addressing the challenges posed by imbalanced datasets and the sophistication of fraud schemes. By implementing a comprehensive detection system using these models on a credit card transaction dataset, the study aims to enhance the accuracy of fraud detection and provide timely alerts to prevent financial losses. Key results indicate that the proposed methodology significantly improves the identification of fraudulent transactions, ultimately leading to more secure credit card usage for consumers. The conclusions drawn from this research emphasize the necessity for ongoing innovation in fraud detection methodologies to keep pace with the ever- changing landscape of financial fraud. (shrink)

This fifth volume on Advances and Applications of DSmT for Information Fusion collects theoretical and applied contributions of researchers working in different fields of applications and in mathematics, and is available in open-access. The collected contributions of this volume have either been published or presented after disseminating the fourth volume in 2015 in international conferences, seminars, workshops and journals, or they are new. The contributions of each part of this volume are chronologically ordered. First Part of this book presents some (...) theoretical advances on DSmT, dealing mainly with modified Proportional Conflict Redistribution Rules (PCR) of combination with degree of intersection, coarsening techniques, interval calculus for PCR thanks to set inversion via interval analysis (SIVIA), rough set classifiers, canonical decomposition of dichotomous belief functions, fast PCR fusion, fast inter-criteria analysis with PCR, and improved PCR5 and PCR6 rules preserving the (quasi-)neutrality of (quasi-)vacuous belief assignment in the fusion of sources of evidence with their Matlab codes. Because more applications of DSmT have emerged in the past years since the apparition of the fourth book of DSmT in 2015, the second part of this volume is about selected applications of DSmT mainly in building change detection, object recognition, quality of data association in tracking, perception in robotics, risk assessment for torrent protection and multi-criteria decision-making, multi-modal image fusion, coarsening techniques, recommender system, levee characterization and assessment, human heading perception, trust assessment, robotics, biometrics, failure detection, GPS systems, inter-criteria analysis, group decision, human activity recognition, storm prediction, data association for autonomous vehicles, identification of maritime vessels, fusion of support vector machines (SVM), Silx-Furtif RUST code library for information fusion including PCR rules, and network for ship classification. Finally, the third part presents interesting contributions related to belief functions in general published or presented along the years since 2015. These contributions are related with decision-making under uncertainty, belief approximations, probability transformations, new distances between belief functions, non-classical multi-criteria decision-making problems with belief functions, generalization of Bayes theorem, image processing, data association, entropy and cross-entropy measures, fuzzy evidence numbers, negator of belief mass, human activity recognition, information fusion for breast cancer therapy, imbalanced data classification, and hybrid techniques mixing deep learning with belief functions as well. (shrink)

Text classification is one of the most important task in natural language processing, In this research, we carried out several experimental research on three (3) of the most popular Text classification NLP classifier in Convolutional Neural Network (CNN), Multinomial Naive Bayes (MNB), and Support Vector Machine (SVN). In the presence of enough training data, Deep Learning CNN work best in all parameters for evaluation with 77% accuracy, followed by SVM with accuracy of 76%, and multinomial Bayes with least performance of (...) 69% accuracy. CNN has the best performance in the presence of large enough training dataset because of the presence of filter/ kernels which help to indentify patterns in text data regardless of their position in the sentence. -/- We repeated the training again with just one-third of our data, at this point SVM comes with the best performance, the performance of CNN noticeably drops but still better than Multinomial Naive Bayes, the reason why SVM works best when we reduce the training data was because of its ability to look for a hyper-plane that creates a boundary between different classes of data so as to properly classify them, so we believed that getting the hyper-plane was more efficient when we reduce the dataset, hence reason for the good performance. Multinomial Naive Bayes have the least performance which we attributed to its assumption of independency between the features which sometimes does not hold true. We concluded that availability of data should be an important factor when choosing classifier for Natural Language Processing Text Classification task. CNN should be use in the presence of enough dataset, and SVM should be use when data is not enough. Multinomial Naive Bayes must not be trusted with state of the art NLP task due to its assumption of independency between the features. (shrink)

A face reveals a lot of information about a person's identity, age, sex, race, and emotional as well as psychological state. Facial expressions are often used in the behavioral interpretation of emotions and play a key role in social interactions. Due to its potential applications such as HCI, behavioral science, automatic facial emotion detection is one of the most intriguing and challenging areas in computer vision. Our Facial Emotion Recognition system performs detection and location of faces in a cluttered scene, (...) facial feature extraction, and facial expression classification. Numerous models were experimented such as decision trees and SVM’s before arriving at a Convolutional Neural Networks (CNN) model. Due to large number of filters, CNNs are efficient for image recognition tasks since they can capture spatial features of the inputs. After observing unbelievable performance with deep learning models, we used deep convolution features to better represent the given image instead of using the traditional handcrafted features. We have proposed and developed a Deep Convolutional Neural Network for classifying human emotions from dynamic facial expressions in real-time. Kaggle’s FER-2013 dataset with seven facial emotions labels as happy, sad, surprise, fear, anger, disgust, and neutral is used to train the model. An overall training accuracy of 92.86% and test accuracy of 64.42% are achieved. Finally, a live video stream connected to a face detector feeds images to the neural network. The network subsequently classifies an arbitrary number of faces per image in real-time simutaneously, wherein appropriate emotions are displayed over the subject’s faces and their probabilities are displayed over a real-time bar graph on a separate window. (shrink)

Coronary Heart Disease (CHD) is one of the leading causes of death nowadays. Prediction of the disease at an early stage is crucial for many health care providers to protect their patients and save lives and costly hospitalization resources. The use of machine learning in the prediction of serious disease events using routine medical records has been successful in recent years. In this paper, a comparative analysis of different machine learning techniques that can accurately predict the occurrence of CHD events (...) from clinical data was performed. Four machine learning classifiers, namely Logistic Regression, Support Vector Machine (SVM), K- Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) Neural Networks were identified and applied to a dataset of 462 medical instances and 9 features as well as the class feature from the South African Heart Disease data retrieved from the KEEL repository. The dataset consists of 302 records of healthy patients and 160 records of patients who suffer from CHD. In order to handle the imbalanced classification problem, the K-means algorithm along with Synthetic Minority Oversampling TEchnique (SMOTE) was used in this study. The empirical results of applying the four machine learning classifiers on the oversampled dataset have been very promising. The results reported using different evaluation metrics showed that SVM has achieved the highest overall prediction performance. (shrink)

Early detection of CKD is essential for timely intervention and improved patient outcomes. This project aims to develop a machine learning-based predictive model for diagnosing CKD at an early stage. By utilizing a range of clinical features such as age, blood pressure, blood sugar, and other relevant biomarkers, we employ machine learning algorithms, including Decision Trees, Random Forests, and Support Vector Machines (SVM), to predict the likelihood of a patient developing CKD.

Due to the development of advanced identity based attacks and even complex cyber threats, merely possessing defensive cyber security capabilities is not enough today. In this study, we investigate how predictive analytics based machine learning (ML) can be employed for pro-active identity management and threat detection. In this study, the authors assess some models of machine learning – Decision Trees, Random Forests, Support Vector Machines (SVM), and a new hybrid one – to determine which best allows for the detection of (...) both known and unknown threats. The results reveal that in metrics such as accuracy, precision, recall, and F1 score. The hybrid model incorporating both supervised and unsupervised learning approaches scored the highest among other models. As a consequence of its adaptability, the hybrid model is capable of real time dynamic threat detection and anomaly based identity management which makes it an appropriate model for the changing cyber security environment. This study provides the prospects to make proactive cybersecurity more efficient and therefore enhancing the technology for protection systems. (shrink)

Chronic kidney disease (CKD) is a global health problem with high morbidity and mortality rate, and it induces other diseases. There are no obvious incidental effects during the starting periods of CKD, patients routinely disregard to see the sickness. Early disclosure of CKD enables patients to seek helpful treatment to improve the development of this disease. AI models can effectively assist clinical with achieving this objective on account of their fast and exact affirmation execution. In this appraisal, proposed a Logistic (...) relapse framework for diagnosing CKD. Proposed calculation like NAIVE BAYES , DECISION TREE , KSTAR , LOGISITIC , AND SVM and look at these calculation and get the most noteworthy precision .AI store, which has an enormous number of missing qualities. Missing characteristics are for the most part found, taking everything into account, clinical conditions since patients might miss a couple of assessments for various reasons. By separating the misjudgements delivered by the set up models and proposed a fused model that unites determined backslide and sporadic woods by using perceptron. (shrink)

The study explores an approach to IT stress detection utilizing deep learning, specifically convolutional neural networks (CNNs), as well as traditional machine learning algorithms including decision trees (DT) and support vector machines (SVM). The research focuses on image processing techniques to extract relevant features from facial expressions and physiological signals indicative of stress. The proposed methodology involves data acquisition, preprocessing, and feature extraction to prepare the input data for model training. CNNs are employed to automatically learn discriminative features directly from (...) the images, while DT and SVM models are trained on extracted features to compare their performance against the deep learning approach. Evaluation metrics such as accuracy, precision, recall, and F1 score are utilized to assess the effectiveness of each algorithm in stress detection. Additionally, the study explores the potential for ensemble methods to combine the strengths of multiple algorithms for improved performance. The results demonstrate the efficacy of deep learning CNNs in accurately identifying stress from image data, with insights into the comparative performance and potential synergies with traditional machine learning techniques. This research contributes to advancing the field of stress detection by leveraging state-of-the-art deep learning methodologies within the context of image processing. (shrink)

Electrocardiogram (ECG) signal analysis is a critical task in healthcare for diagnosing cardiovascular conditions such as arrhythmias, heart attacks, and other heart-related diseases. With the growth of Internet of Things (IoT) networks, real-time ECG monitoring has become possible through wearable devices and sensors, providing continuous patient health monitoring. However, real-time ECG signal analysis in IoT environments poses several challenges, including data latency, limited computational power of IoT devices, and energy constraints. This paper proposes a framework for Optimized Machine Learning Algorithms (...) designed to analyze ECG signals in real time within IoT networks. The proposed system leverages lightweight machine learning models, including support vector machines (SVM) and convolutional neural networks (CNNs), optimized to run efficiently on low-power IoT devices while maintaining high accuracy. The system addresses the computational limitations of IoT devices by employing edge computing techniques that distribute the processing load between IoT devices and edge servers. Additionally, data compression and feature extraction techniques are applied to reduce the size of the data transmitted over the network, thereby minimizing latency and bandwidth usage. This paper reviews the current advancements in real-time ECG analysis, explores the challenges posed by IoT environments, and presents the optimized machine learning algorithms that enhance real-time monitoring of heart health. The system is evaluated for its performance in terms of accuracy, energy efficiency, and data transmission speed, showing promising results in improving real-time ECG signal analysis in resource-constrained IoT networks. (shrink)

This paper represents the classification and analysis of sleep apnea using machine learning techniques. Now a days Sleep apnea is a sleeping disorder affecting more than 20 % of all American adults, associated with intermittent air passageway obstruction during sleep. This results in intermittent hypoxia, sympathetic activation, and an interruption of sleep with various health consequences. The diagnosis of sleep apnea traditionally involves the performance of overnight polysomnography, where oxygen, heart rate, and breathing, among other physiologic variables, are continuously monitored (...) during sleep at a sleep center. However, these sleep studies are expensive and impose access issues, given the number of patients who need to be diagnosed. There is hence utility in having an effective triage system to screen for OSA to utilize polysomnography better. In this study, we plan to explore using several machine learning algorithms to utilize pre-screening symptoms to diagnose obstructive sleep apnea (OSA). In the experimental results, it was found that Decision Tree Classifier (DTC) and Random Forest (RF) provided the highest classification accuracies compared to other algorithms such as Logistic Regression (LR), Support Vector Machines (SVM), Gradient Boosting Classifier (GBC), Gaussian Naive Bayes (GNB), K Neighbors Classifier (KNC). (shrink)

The rise of social media has created a new platform for communication and interaction, but it has also facilitated the spread of harmful behaviors such as cyberbullying. Detecting and mitigating cyberbullying on social media platforms is a critical challenge that requires advanced technological solutions. This paper presents a novel approach to cyberbullying detection using a combination of supervised machine learning (ML) and natural language processing (NLP) techniques, enhanced by optimization algorithms. The proposed system is designed to identify and classify cyberbullying (...) behavior in real-time, analyzing textual data from social media posts to detect harmful content. The model is trained on a large dataset of labeled instances of bullying and non-bullying content, using supervised ML algorithms such as Support Vector Machines (SVM), Decision Trees, and Random Forest. NLP techniques, including sentiment analysis, keyword extraction, and text vectorization, are employed to preprocess and transform the data into a format suitable for machine learning. To optimize the performance of the detection model, techniques such as Grid Search, Genetic Algorithms, and Particle Swarm Optimization are used to fine-tune hyperparameters, resulting in improved accuracy and reduced false positives. The system's effectiveness is validated through experiments conducted on various social media platforms, demonstrating its potential to detect cyberbullying with high precision. Future work will focus on enhancing the model's adaptability to emerging slang and evolving language patterns in social media. Key words: Cyberbullying Detection, Social Media, Supervised Machine Learning, Natural Language Processing (NLP), Optimization Techniques. (shrink)

The rise of social media has created a new platform for communication and interaction, but it has also facilitated the spread of harmful behaviors such as cyberbullying. Detecting and mitigating cyberbullying on social media platforms is a critical challenge that requires advanced technological solutions. This paper presents a novel approach to cyberbullying detection using a combination of supervised machine learning (ML) and natural language processing (NLP) techniques, enhanced by optimization algorithms. The proposed system is designed to identify and classify cyberbullying (...) behavior in real-time, analyzing textual data from social media posts to detect harmful content. The model is trained on a large dataset of labeled instances of bullying and non-bullying content, using supervised ML algorithms such as Support Vector Machines (SVM), Decision Trees, and Random Forest. NLP techniques, including sentiment analysis, keyword extraction, and text vectorization, are employed to preprocess and transform the data into a format suitable for machine learning. To optimize the performance of the detection model, techniques such as Grid Search, Genetic Algorithms, and Particle Swarm Optimization are used to fine-tune hyperparameters, resulting in improved accuracy and reduced false positives. The system's effectiveness is validated through experiments conducted on various social media platforms, demonstrating its potential to detect cyberbullying with high precision. Future work will focus on enhancing the model's adaptability to emerging slang and evolving language patterns in social media. (shrink)