Proactive Detection of Pothole and Walkable Path for Safe Mobility of Visually Challenged

Machine Learning (ML) has been a critical computational paradigm that has shaped contemporary applications in such domains as finance, healthcare, and cybersecurity, such that its performance evaluation cannot be less critical. However, its selection and interpretation of metrics has remained inconsistent, often leading to misleading conclusions. This study presents a systematic analysis of the most commonly used performance evaluation metrics in ML, integrating conceptual taxonomy, mathematical definitions, and empirical assessment under controlled perturbations. There are three dimensions to ML performance evaluation metrics categorization: robustness, discrimination, and calibration. Experiment conducted on classification and regression, and using synthetic datasets and benchmarks, evaluate threshold variation, class imbalance and label noise. Results obtained showed that no single metric captures model performance comprehensively and widely used metrics may yield conflicting or misleading assessments under certain conditions. Also, context-aware selection and multi-dimensional reporting were necessary for reliable evaluation. By empirically linking metric behaviour to data characteristics, this study provides guidance for context-aware metric selection and reporting that is not only standardized but also evidence-based.

SQL Injection attacks is a common threat to web applications that utilizes poor input validation to implement attack on a target database. It is becoming a very serious problem in web application as successful leads to loss of integrity and confidentiality and this makes it a very sensitive issue of software security. This study gives a review on SQL Injection detection and prevention techniques using machine learning classifiers. Machine Learning approach has been found to be profound for SQLIA mitigation, which is implemented through defensive coding approach. An experimental analysis was performed to evaluate the performance of the learning classification algorithms to choose the best algorithm. It is imperative to note that a good number of the evaluated techniques were able to detect and prevent the SQLIA based on the KDD Test dataset. From the findings, Naive Bayes had the minimum Accuracy 80.01%, Sensitivity as well as Specificity while Decision Tree had the highest Accuracy 98.11%, Sensitivity and Specificity and therefore was chosen as the best classifier for SQLIA detection and prevention. Therefore, beyond Accuracy, other performance evaluation metrics are critical for optimal algorithm selection for predictive analytics.

Sickle cell disease (SCD) is a common serious genetic disease, which has a severe impact due to red blood cell (RBCs) abnormality. According to the World Health Organisation, 7 million newborn babies each year suffer either from the congenital anomaly or from an inherited disease, primarily from thalassemia and sickle cell disease. In the case of SCD, recent research has shown the beneficial effects of a drug called hydroxyurea/hydroxycarbamide in modifying the disease phenotype. The clinical management of this disease-modifying therapy is difficult and time consuming for clinical staff. This includes finding an optimal classifier that can help to solve the issues with missing values, multi-class datasets, and features selection. For the classification and discriminant analysis of SCD datasets, 7 classifiers based on machine learning models are selected representing linear and non-linear methods. After running these classifiers with a single model, the results revealed that a single classifier has provided us with effective outcomes in terms of the classification performance evaluation metric. In order to produce such an optimal outcome, this research proposed and designed combined classifiers (ensemble classifiers) among the neural network’s models, the random forest classifier, and the K-nearest neighbour classifier. In this aspect, combining the levenberg-marquardt algorithm, the voted perceptron classifier, the radial basis neural classifier, and random forest classifier obtain the highest rate of performance and accuracy. This ensemble classifier receives better results during the training set and testing set process. Recent technology advances based on smart devices have improved the medical facilities and become increasingly popular in association with real-time health monitoring and remote/personal health-care. The web-based system developed under the supervision of the haematology specialist at the Alder Hey Children’s Hospital in order to produce such an effective and useful system for both patients and clinicians. To sum up, the simulation experiment concludes that using machine learning and the web-based system platforms represents an alternative procedure that could assist healthcare professionals, particularly for the specialist nurse and junior doctor to improve the quality of care with sickle cell disorder.

Researchers are interested in genomic level cancer classification because it offers a thorough, precise, and reliable diagnosis for various cancer types. The gene expression data set is made up of hundreds of samples, each containing thousands of genes. As a result, accurately and effectively classifying such samples is difficult. To analyze gene expression patterns efficiently, recent studies have used artificial intelligence, data mining, and statistical techniques. Furthermore, machine learning methods have been extensively used to construct robust and accurate classification frameworks. In this paper, we examined the effectiveness of machine learning-based classification techniques such as Support Vector Machine, Logistic Regression, Naïve Bayes, Decision Tree, K-Nearest Neighbors, and Random Forest methods. In a total of 72 patients, 7129 distinct gene expressions and their degrees were evaluated to determine their relevance. Features have been normalized and PCA was used to decrease the dataset's dimensionality and complexity. The dataset was divided into training and test sets, with 90% of the occurrences in the training set and 10% in the test set. And finally, SMOTE was employed to oversample the minority class. In this study, gene expression data was utilized to differentiate Acute Myeloid Leukemia (AML) from Acute Lymphoblastic Leukemia (ALL). To evaluate the performance of the six machine learning models we used, we examined their associated confusion matrices and calculated nine performance evaluation metrics for each model's prediction on the test dataset. Results demonstrate that SVM, Logistic Regression, and Naïve Bayes outperformed the other ML techniques with an accuracy of 100%.

A machine learning framework to predict kidney graft failure with class imbalance using Red Deer algorithm

<p>Accurate water level (WL) forecasting is important for water resources management and planning purposes in the Great Lakes. The objectives of this research are two-fold.  The first objective is to apply machine learning (ML) (i.e., random forest (RF) and support vector regression (SVR)) and hybrid convolutional neural network(CNN)-long-short term memory (LSTM) deep learning (DL) models for multi-step (i.e., one-, two- and three-monthly step ahead) WL forecasting in the Great Lakes (Michigan and Ontario). The second objective is to integrate the boundary corrected (BC) maximal overlap discrete wavelet transform (MODWT) with SVR, RF, and CNN-LSTM models to improve the performance of the individual models. By employing a BC-wavelet decomposition method, the ‘future data’ issue (i.e., data from the future that is not available), often overlooked in the literature and a major barrier to achieving realistic forecasting performance is overcome. </p><p>For Lakes Michigan and Ontario, 1212 monthly WL (m) records (spanning Jan 1918–Dec 2018) were used to develop the models. For the non-wavelet-based models (SVR, RF, and CNN-LSTM), candidate model inputs included the WL recorded over the previous 12 months.  For the BC-MODWT-based models (BC-MODWT-SVR, BC-MODWT-RF, and BC-MODWT-CNN-LSTM), the lagged input time series were decomposed into BC-wavelet and scaling coefficients by using different mother wavelets (Haar, Daubechies, Symlets, Fejer-Korovkin and Coiflets), filter lengths (from two up to 12) and decomposition levels (from one up to seven).  For each method (SVR, RF, and CNN-LSTM), mother wavelet, and decomposition level a model was generated.  For both wavelet- and non-wavelet-based models, the particle swarm optimization (PSO) method was used to select the most appropriate inputs to include in the proposed multi-step WL forecasting models.</p><p>The datasets were partitioned into calibration and validation subsets. After calibrating the models, various performance evaluation metrics, e.g., coefficient of determination (R<sup>2</sup>), root mean square error (RMSE), mean absolute error (MAE), root mean square percentage error (RMSPE), mean absolute percentage error (MAPE) and the Nash-Sutcliffe efficiency coefficient (NSC) were used to assess model accuracy.</p><p>Of the ML models, the SVR outperformed RF while the DL models outperformed the ML models for each forecast lead time (one-, two-, and three-step(s) ahead). Results from this case study indicate that not all wavelet families and decomposition levels perform equally and in some cases, the wavelet-based models do not improve performance over the non-wavelet-based models. However, the BC-MODWT-CNN-LSTM using suitable mother wavelets (e.g., Haar) outperforms the individual ML and BC-MODWT-ML-based models. More accurate forecasts were obtained for Lake Michigan although the performance in both Great Lakes was accurate. The outcomes of this research indicate that the BC-MODWT-CNN-LSTM model is a promising tool for generating accurate WL forecasts.</p>

Human Action Recognition (HAR) is a vital part of the healthcare sector. Medical practitioners are experiencing difficulty in recognizing human physiological conditions due to the enormous quantity of sensory stimulation. Machine learning techniques help to predict human physiological conditions, providing medical practitioners to work more efficiently. Feature selection is an essential part of discovering new knowledge in the majority of real-world problems when there are a lot of features. Feature selection is extremely useful because it speeds up decisions and enhances classification performance. The importance of feature selection in machine learning is dimension reduction in a massive multivariate data collection. This paper presents an effective feature selection method known as the Enhanced Recursive Feature Elimination (EFRE) for selecting key features from the data set for HAR prediction. The experimental results reveal that the ERFE technique selects the most suitable features for HAR prediction. The performance of the proposed ERFE approach is tested using different performance evaluation metrics. The performance analysis shows that the ERFE method outperforms existing feature selection methods with 88% accuracy.

Aim: In addition to affecting the individual sociologically and psychologically, heart disease also poses important problems in health systems. Evaluation of heart disease performances has gained great importance in terms of machine learning method. In the study, performances were compared with the machine learning method for risk methods that classify heart illness. Materials and Methods: The categorization process Throughout the research made use of the "Heart Disease Dataset," an open access dataset. F1-score, sensitivity, selectivity, accuracy, balanced accuracy, negative and positive predictive values were used to assess the performance of the categorisation model using the machine learning approach. Random forest method, one of the variable selection methods, was used. Results: According to the relational classification model's classification findings for heart disease, the accuracy, balanced accuracy, sensitivity, selectivity, positive predictive value, negative predictive value, and F1-score values were observed to be 0.997, 0.997, 0.995, 1, 1, and 0.995, respectively. Conclusion: The relational classification model proposed in the analysis obtained in the web-based open access dataset yielded distinctively successful results in classifying heart disease according to performance criteria.

The ongoing increase in urban populations has intensified the persistent issue of traffic congestion, negatively impacting the quality of life by increasing commute times, compromising road safety, and deteriorating local air quality. As a result, identifying and forecasting traffic congestion patterns has become critical, positioning Traffic Congestion Prediction (TCP) as a rapidly growing field of study. Recent advancements in Machine Learning (ML), Artificial Intelligence (AI), and Internet of Things (IoT) sensor technologies have further underscored the importance of TCP in the development of Intelligent Transportation Systems (ITS).This review paper explores advanced TCP methodologies, with a particular emphasis on innovative forecasting techniques and technologies vital to the ITS domain. We provide a comprehensive overview of statistical and machine learning approaches, including hybrid and ensemble models, that are commonly used for TCP. Additionally, the paper discusses various forecasting techniques and elaborates on performance evaluation metrics from both regression and classification perspectives.To provide a practical framework, a standardized step-bystep methodology often adopted in TCP problems is presented. As part of the implementation, a KNearest Neighbors (KNN) classifier was employed as the proposed predictive model. Comparative evaluation revealed that KNN outperformed the Logistic Regression model in terms of both accuracy and robustness in predicting traffic congestion events. The results validate the potential of data-driven approaches to enhance proactive traffic management and informed decision-making in the context of smart cities

Deep learning models for solar irradiance forecasting: A comprehensive review

—Stress is a common psychological state that significantly impacts human well-being, productivity, and overall health. The ability to accurately detect stress in individuals is crucial for mitigating its harmful effects. In recent years, machine learning (ML) and deep learning (DL) have emerged as powerful tools for stress detection, utilizing physiological data, behavioral cues, and other relevant information. This survey paper provides a comprehensive review of the existing ML and DL approaches used for stress detection, exploring a wide range of models, datasets, and applications. We highlight various techniques, including supervised and unsupervised learning, feature extraction methods, and performance evaluation metrics. Additionally, the challenges in the field, such as data heterogeneity, real- time detection, and model interpretability, are discussed, along with future research directions that could further enhance the effectiveness of stress detection systems.

Numerical electronic health records often come with numerous features and outliers. These features are usually indicators of medical diseases. To prevent poor model performance associated with the curse of dimensionality, these features must be reduced with only the most important ones retained. Also, outliers may result in poor generalization and performance of a machine learning model. This study investigates the impact of dimensionality reduction and outliers on machine learning models for medical disease diagnosis. After fitting datasets to the models, the impact of outliers and dimensionality reduction was evaluated using performance evaluation metrics. The accuracy for all models across the Wisconsin breast and heart dataset illustrates a minimum of 1.5% increase compared to when PCA was not implemented. Also, the precision, recall, and f1 score values show significant improvement. The naïve Bayes model recorded an accuracy of 73.6% in the absence of outliers and 72.7% in the presence of outliers when the Pima Indian diabetes dataset was used. This is less than 1% improvement in the model’s performance. The result indicates that dimensionality reduction significantly impacts the performance of models in diagnosing breast cancer and heart disease. Furthermore, outliers did not significantly impact the model’s performance when using Pima Indian and stroke datasets. Finally, this study depicts that problems associated with the curse of dimensionality persist with machine learning models in diagnosing medical diseases.

Hardware Trojans (HTs) pose a serious threat to integrated circuit (IC) security. Detection of HTs is extremely challenging due to their stealthy nature. Side-channel analysis techniques have emerged as promising approaches for HT detection by observing anomalies in physical parameters like power or delay. More recently, machine learning (ML) methods have been explored to enhance the accuracy and efficiency of side-channel based HT detection. Background: This paper presents a novel approach using machine learning techniques to detect stealthy hardware Trojans through side-channel analysis. Hardware Trojans, malicious modifications inserted into integrated circuits during manufacturing, pose significant threats to the integrity and security of electronic systems. Traditional methods of detecting these Trojans often rely on known signatures or specific patterns, making them ineffective against subtle and sophisticated attacks. Method: This paper provides a comprehensive review of research advancements in applying ML for side-channel based HT detection. First, an overview of HT attacks, their classification, threat models and detection challenges is presented. Next, various side-channel parameters like power, temperature, delay and electromagnetic emanations used for HT detection are discussed along with their merits and demerits. Furthermore, the application of supervised, unsupervised and semi-supervised ML algorithms for automated feature extraction and intelligent decision making is elucidated in detail. Result: Specifically, the data collection strategies, feature extraction techniques, ML models and performance evaluation metrics adopted in existing literature are critically reviewed. In addition, the limitations of current approaches and promising future research directions like on-chip ML implementation, hierarchical ML and explainable ML models tailored for HT detection are highlighted. Conclusion: Case studies on benchmark circuits are also presented to demonstrate the efficacy of ML-based side-channel HT detection methods. Through an extensive literature review and incisive analysis, this paper provides contemporary insights on the advancement of ML techniques to enable robust side-channel based HT detection for securing next-generation ICs.

In this work, we studied the use of Quantum Machine Learning (QML) algorithms for binary classification and compared their performance with classical Machine Learning (ML) methods. QML merges principles of Quantum Computing (QC) and ML, offering improved efficiency and potential quantum advantage in data-driven tasks and when solving complex problems. In binary classification, where the goal is to assign data to one of two categories, QML uses quantum algorithms to process large datasets efficiently. Quantum algorithms like Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) exploit quantum parallelism and entanglement to enhance performance over classical methods. This study focuses on two common QML algorithms, Quantum Support Vector Classifier (QSVC) and QNN. We used the Qiskit software and conducted the experiments with three different datasets. Data preprocessing included dimensionality reduction using Principal Component Analysis (PCA) and standardization using scalers. The results showed that quantum algorithms demonstrated competitive performance against their classical counterparts in terms of accuracy, while QSVC performed better than QNN. These findings suggest that QML holds potential for improving computational efficiency in binary classification tasks. This opens the way for more efficient and scalable solutions in complex classification challenges and shows the complementary role of quantum computing.

Cybercriminals have increasingly leveraged sophisticated techniques to bypass traditional signature-based detection systems through the use of Ransomware-as-a-Service (RaaS) platforms, double and triple extortion strategies, and advanced evasion mechanisms. As a result, ransomware attacks have reached unprecedented levels. Using this systematic evaluation framework, we examine the current state and effectiveness of machine learning (ML) and deep learning (DL) approaches for ransomware detection, addressing critical gaps in existing research methodologies while providing comprehensive recommendations for future research. The study analyses multiple AI paradigms including supervised learning algorithms such as Random Forests and Support Vector Machines, unsupervised techniques such as clustering and anomaly detection, and deep learning architectures such as Convolutional Neural Networks and Long Short-Term Memory networks. Hybrid approaches combining static and dynamic analysis consistently achieve superior performance, with accuracy rates exceeding 99% when properly implemented. As part of the framework, fundamental challenges are addressed such as dataset quality and diversity, feature extraction and selection methodologies, data preprocessing techniques, and performance evaluation metrics that have been tailored specifically for cybersecurity applications. Several findings indicate that ensemble learning methods outperform individual classifiers, with Random Forest algorithms being particularly effective at handling high-dimensional feature spaces while maintaining interpretability for security analysts. As a result of the study, significant limitations have been identified in current research, including an overreliance on static data sets that do not capture evolving threat landscapes, an inadequate representation of modern attack vectors, and a limited ability to generalize across different operational environments. Future directions of this research include explainable AI integration for transparent decision-making, adaptive real-time detection systems, and federated learning approaches for collaborative threat intelligence sharing while maintaining organizational privacy. It provides standardized methodologies for data curation, feature engineering, model development, and performance benchmarking, enabling fair comparisons between different AI approaches and facilitating reproducible research. This work contributes to essential guidance for cybersecurity practitioners, policymakers, and researchers in developing robust, adaptive, and interpretable ransomware detection systems capable of defending against increasingly sophisticated cyber threats while considering ethical concerns and regulatory compliance requirements in modern digital ecosystems.