Early diagnosis of medical conditions in infants is crucial for ensuring timely and effective treatment. However, infants are unable to verbalize their symptoms, making it difficult for healthcare professionals to accurately diagnose their conditions. Crying is often the only way for infants to communicate their needs and discomfort. In this paper, we propose a medical diagnostic system for interpreting infants’ cry audio signals (CAS) using a combination of different audio domain features and deep learning (DL) algorithms. The proposed system utilizes a dataset of labeled audio signals from infants with specific pathologies. The dataset includes two infant pathologies with high mortality rates, neonatal respiratory distress syndrome (RDS), sepsis, and crying. The system employed the harmonic ratio (HR) as a prosodic feature, the Gammatone frequency cepstral coefficients (GFCCs) as a cepstral feature, and image-based features through the spectrogram which are extracted using a convolution neural network (CNN) pretrained model and fused with the other features to benefit multiple domains in improving the classification rate and the accuracy of the model. The different combination of the fused features is then fed into multiple machine learning algorithms including random forest (RF), support vector machine (SVM), and deep neural network (DNN) models. The evaluation of the system using the accuracy, precision, recall, F1-score, confusion matrix, and receiver operating characteristic (ROC) curve, showed promising results for the early diagnosis of medical conditions in infants based on the crying signals only, where the system achieved the highest accuracy of 97.50% using the combination of the spectrogram, HR, and GFCC through the deep learning process. The finding demonstrated the importance of fusing different audio features, especially the spectrogram, through the learning process rather than a simple concatenation and the use of deep learning algorithms in extracting sparsely represented features that can be used later on in the classification problem, which improves the separation between different infants’ pathologies. The results outperformed the published benchmark paper by improving the classification problem to be multiclassification (RDS, sepsis, and healthy), investigating a new type of feature, which is the spectrogram, using a new feature fusion technique, which is fusion, through the learning process using the deep learning model.

Selecting the appropriate undergraduate program is a critical decision for students. Many elements influence this choice for secondary students, including financial, social, demographic, and cultural factors. If a student makes a poor choice, it will have implications for their academic life as well as their professional life. These implications may include having to change their major, which will cause a delay in their graduation, having a low grade-point average (GPA) in their chosen major, which will cause difficulties in finding a job, or even dropping out of university. In this paper, various supervised machine learning techniques, including Decision Tree, Random Forest, and Support Vector Machine, were investigated to predict undergraduate majors. The input features were related to the student’s academic history and the job market. We were able to recommend the program that guarantees both a high academic degree and employment, depending on previous data and experience, for Master of Business Administration (MBA) students. This research was conducted based on a published research and using the same dataset and aimed to improve the results by applying hyper-tuning, which was absent in previous research. The obtained results showed that our work outperformed the work of the published research, where the random forest exceeded the other classification techniques and reached an accuracy of 97.70% compared to 75.00% on the published research. The importance of features was also investigated, and it was found that the degree percentage, MBA percentage, and entry test result were the top contributing features to the model.

This study compares expert-based multi-criteria decision analysis (MCDA) with the traditional Pavement Condition Index (PCI) for prioritizing pavement maintenance. Using data on PCI, traffic volume, crashes, costs, and public complaints, along with weights from 35 experts, the research developed different prioritization scenarios. The MCDA approach, using average expert weights, assigned the highest importance to public complaints (PC: 30.7%) and traffic volume (ADT: 17.9%), significantly shifting priorities from the PCI-only method. Sensitivity analysis revealed the ranking framework is robust, with results remaining consistent despite moderate variations in expert judgment. The factors most influential in changing rankings were public complaints (PC), crash data (CR), and maintenance cost (MC). The findings demonstrate that integrating expert judgment with objective data creates more robust and inclusive maintenance plans, providing valuable insights for transportation agencies.

Accurate and scalable driver performance assessment is critical for improving road safety and reducing traffic-related injuries and fatalities, particularly in low- and middle-income countries where the majority of global road deaths occur. This paper presents an exploratory proof-of-concept framework for automated driver evaluation that combines real-world dashcam footage, YOLOv8-based object detection, and multimodal large language models (MLLMs), specifically Gemini 1.5 Flash. Two prompting strategies, narrative and rule-based, were designed to assess driver behavior against standardized licensing criteria derived from the California Department of Motor Vehicles (DMV) driving performance evaluation score sheet. The framework was evaluated across 11 manually curated driving scenarios covering intersections, pedestrian crossings, stop signs, cyclists, and emergency vehicles. Ground-truth labels were established through consensus between two traffic engineering experts cross-referencing official California DMV evaluation criteria. In this preliminary evaluation, the rule-based prompt achieved higher agreement with ground-truth assessments (10/11 scenarios, 90.9%) compared to the narrative prompt (7/11 scenarios, 63.6%), particularly in detecting clear rule violations. The narrative approach demonstrated greater contextual flexibility in ambiguous situations. These results should be interpreted as preliminary, given the small sample size, manually curated dataset, and absence of large-scale statistical validation. Nonetheless, the findings illustrate how combining visual detection with structured language-model prompting may support interpretable, policy-aligned driver evaluation. Key limitations include dependence on video quality, limited scenario diversity, absence of temporal behavioral modeling, and reproducibility constraints tied to proprietary API behavior. Future work should expand validation to larger annotated datasets, incorporate temporal sequence modeling, and explore region-specific regulatory adaptation.