Drowsiness has been recognized as a leading factor in road accidents worldwide. Despite considerable research in this area, this paper aims to improve the precision of drowsiness detection specifically for long-haul travel by employing the Dlib-based facial feature detection algorithm. This study proposes two algorithms: a static and adaptive frame threshold. Both approaches utilize eye closure ratio (ECR) and mouth aperture ratio (MAR) parameters to determine the driver’s level of drowsiness. The static threshold method issues a warning when the ECR and/or MAR values reach specific thresholds. In this method, the ECR threshold is established at 0.15 and the MAR threshold at 0.4. The static threshold method demonstrated an accuracy of 89.4% and a sensitivity of 96.5% using 1000 images. The adaptive frame threshold algorithm uses a counter to monitor the number of consecutive frames that meet the drowsiness criteria before triggering a warning. Additionally, the number of consecutive frames required is adjusted dynamically over time to enhance detection accuracy and more accurately indicate a state of drowsiness. The adaptive frame threshold algorithm was tested using four 30 min videos, from a publicly available dataset achieving a maximum accuracy of 98.2% and a sensitivity of 64.3% with 500 images.

Especially NMC-LCO 18650 cells, lithium-ion batteries are essential parts of electric vehicles (EVs), where their dependability and performance directly affect operating efficiency and safety. Predictive maintenance, cost control, and increasing user confidence in electric vehicle technology depend on accurate Remaining Useful Life (RUL) forecasting of these batteries. Using advanced machine learning models, this research uses past usage data and essential performance characteristics to forecast the RUL of NMC-LCO 18650 batteries. The work creates a scalable and web-based application for RUL prediction by utilizing predictive models like Long Short-Term Memory (LSTM), Linear Regression (LR), Artificial Neural Network (ANN), and Random Forest with Extra Trees Regressor (RF with ETR) with results in Mean Square Error (MSE) as accuracy as 96%, 97%, 98% and 99% respectively. This research also emphasizes the importance of algorithm design that can provide reliable RUL predictions even in cases when cycle count data is lacking by properly using alternative features. On further investigation, our findings highlighted that the introduction of cycle count as a feature is critical for significantly reducing the mean squared error (MSE) in all four models. When the cycle count is included as a feature, the MSE for LSTM decreases from 12,291.69 to 824.15, the MSE for LR decreases from 3363.20 to 51.86, the MSE for ANN decreases from 2456.65 to 1858.31, and finally, the RF with ETR decreases from 384.27 to 10.23, which makes it the best performing model considering these two crucial performance metrics. Apart from forecasting the remaining useful life of these lithium-ion batteries, the web application gives options for selecting a model amongst these models for prediction and further classifies battery condition and advises best use practices. Conventional approaches for battery life prediction, such as physical disassembly or electrochemical modeling, are resource-intensive, ecologically destructive, and unfeasible for general use. On the other hand, machine learning-based methods use extensive real-world data to generate scalable, accurate, and efficient forecasts.

Agriculture is a major economic industry that sustains life. Moreover, plant health is a crucial aspect of a highly functional agricultural system. Because stress agents can damage crops and plants, it is important to understand what effect these agents can have and be able to detect this negative impact early in the process. Machine learning technology can help to prevent these undesirable consequences. This research investigates machine learning applications for plant health analysis and classification. Specifically, Residual Networks (ResNet) and Long Short-Term Memory (LSTM) models are utilized to detect and classify plants response to abiotic external stressors. Two types of plants, azalea (shrub) and Chinese tallow (tree), were used in this research study and different concentrations of sodium chloride (NaCL) and acetic acid were used to treat the plants. Data from cameras and soil sensors were analyzed by the machine learning algorithms. The ResNet34 and LSTM models achieved accuracies of 96% and 97.8%, respectively, in classifying plants with good, medium, or bad health status on test data sets. These results demonstrate that machine learning algorithms can be used to accurately detect plant health status as well as healthy and unhealthy plant conditions and thus potentially prevent negative long-term effects in agriculture.

Superconductors have a wide array of applications, such as medical imaging, supercomputing, and electric power transmission, but superconducting materials only operate at very cold temperatures. Thus, the quest to engineer room temperature superconductors is currently a hot topic of research. To accomplish this mission, it is important to have a complete understanding of the material properties that are being used to create these superconductors. Understanding the atomic and electromagnetic properties of the prospective materials will provide tremendous insight into the best choice for the materials. Therefore, a theoretical model that incorporates electromagnetic field theory and quantum mechanics principles is utilized to explain the electrical and magnetic characteristics of superconductors. This model can be used to describe the electrical resistance response and why it vanishes at the material’s critical temperature. The model can also explain the behavior of magnetic fields and why some superconducting materials completely exclude magnetic fields while other superconductors partially exclude these fields. Thus, this theoretical analysis produces a model that describes the behavior of both type I and type II superconductors. Since there are subtle differences between superconductors and perfect conductors, this model also accounts for this distinction and explains why superconductors behave differently than perfect conductors. Therefore, this theory addresses the major properties associated with superconducting materials and thus will aid researchers in the pursuit of designing room temperature superconductors.

Epilepsy affects approximately 50 million people worldwide, and timely, accurate seizure detection is essential for clinical management. Electroencephalogram (EEG) signals carry rich temporal and spectral information about brain dynamics, yet manual interpretation is time-consuming and expert-dependent. This paper presents a complete automated EEG classification pipeline combining signal processing feature engineering with supervised machine learning to distinguish epileptic from non-epileptic brain states. Using the UCI Epileptic Seizure Recognition Dataset (11,500 segments of approximately 1.025 s and five classes at 173.61 Hz), we extract 31 features spanning the time domain (mean, standard deviation, RMS, peak-to-peak, zero-crossing rate, skewness, kurtosis, Hjorth activity, mobility, complexity, line length, mean absolute deviation, and derivative variance) and the frequency domain (DFT magnitude statistics and Welch PSD statistics, spectral entropy, spectral centroid, spectral bandwidth, total power, EEG band powers (delta through gamma), and inter-band power ratios). Four classifiers—logistic regression (LR), random forest (RF), support vector machine (SVM), and gradient boosting (GB)—are trained and evaluated on a binary task (seizure versus non-seizure) and a five-class task. For binary classification, the SVM achieves the highest accuracy of 99.13% with an F1 score of 0.978. For multiclass classification, gradient boosting achieves 81.35% accuracy. Feature importance analysis identifies the Hjorth complexity, spectral centroid, and theta-band power as the most discriminative features. A comprehensive ablation study further confirms that the combined 31-feature representation outperforms either domain in isolation by up to 4.2 percentage points on the multiclass task. Unlike less interpretable deep learning models, the proposed signal processing pipeline is computationally efficient and provides transparent feature-based classification on this benchmark dataset. The complete pipeline is implemented in Python 3.13.15 and is fully reproducible.