Over the last decade, the world has witnessed many breakthroughs in artificial intelligence, largely due to advances in deep learning technology. Notably, computer vision solutions have significantly contributed to these achievements. Human face analysis, a core area of computer vision, has gained considerable attention due to its wide applicability in fields such as law enforcement, social media, and marketing. However, existing methods for facial age estimation often struggle with accuracy due to limited feature extraction capabilities and inefficiencies in learning hierarchical representations. This paper introduces a novel framework to address these issues by proposing a Multi-Stage Deep Neural Network (MSDNN) architecture. The MSDNN architecture divides each CNN backbone into multiple stages, enabling more comprehensive feature extraction, thereby improving the accuracy of age predictions from facial images. Our framework demonstrates a significant performance improvement over traditional solutions, with its effectiveness validated through comparisons with the EfficientNet and MobileNetV3 architectures. The proposed MSDNN architecture achieves a notable decrease in Mean Absolute Error (MAE) across three widely used public datasets (MORPH2, CACD, and AFAD) while maintaining a virtually identical parameter count compared to the initial backbone architectures. These results underscore the effectiveness and feasibility of our methodology in advancing the field of age estimation, showcasing it as a robust solution for enhancing the accuracy of age prediction algorithms.

Pharmaceutical manufacturing has surged in drug development with the rise of Pharma 4.0, leveraging artificial intelligence (AI) to improve efficiency, optimize resource use, and reduce production times. Direct Tablet Compression (DTC), a key manufacturing technique, depends on the physicochemical properties of active pharmaceutical ingredients (API), excipients, and process parameters. This paper presents a novel multi-task framework combining regression, classification, and text generation to predict tablet properties (friability, hardness, disintegration time, and water absorption ratio), determine batch acceptance, and provide insights for optimizing interactions to improve tablet quality. The framework not only enables real-time monitoring, quality control and regulatory compliance, but also helps to understand the reasons why tablets in the manufacturing batch do not meet quality requirements. Using statistical methods, Neural Networks (NN), Natural Language Processing (NLP), and generative AI (GenAI), it outperforms state-of-the-art methods, achieving 91.8% R² and 95.5% accuracy for regression and classification, respectively, as demonstrated using the Harvard Dataverse V1 dataset of Fast Disintegrating Tablets (FDTs) non placebo.

Driver fatigue significantly contributes to road accidents and fatalities, particularly during late-night or early-morning travel due to lack of sleep. Fatigue impairs attention and delays reaction times, increasing accident risk. The American Automobile Association estimates that drowsy driving causes over 320,000 accidents annually, resulting in approximately 6,400 fatal collisions. Building effective drowsiness detection systems has therefore become a paramount need. This paper introduces a novel neural solution for drowsiness detection from the driver’s face using a semi-supervised learning technique. The framework integrates YOLOv8 for accurate face detection and the Swin Transformer to extract subtle fatigue cues using hierarchical attention. An adaptive pseudo-labeling strategy with dynamic confidence thresholding reliably expands the training set, directly improving model robustness. A comprehensive evaluation on the NTHU-DDD, YawDD, and UTA-RLDD datasets demonstrates superior performance, achieving accuracies of 99.99%, 99.34%, and 95.94%, respectively, while maintaining a runtime processing speed of 52.12 frames per second (FPS). The proposed approach outperforms state-of-the-art methods. Ablation studies confirm the effectiveness of both the Swin Transformer backbone and the semi-supervised learning components.

Cross-border trade barriers introduced by national authorities to protect local business and labor force cause substantial damage to international economical actors. Therefore, identifying such barriers beyond regulator’s audit reporting is of paramount importance. This paper contributes towards this goal by proposing a novel approach that uses natural language processing and deep learning method for uncovering Finnish-Russian trade barriers in the fish industry from selected business discussion forums. Especially, the approach makes use i) a three-leg ontology for data collection, ii) a BERT architecture for mapping Onkivisit-Shaw-Kananen trade barrier ontology to negative polarity posts and, iii) a new reverse-engineering clustering approach to identify the causes of individual trade-barrier types. A comparison with official statistical reports has been carried out to identify the salient aspects of trade-barriers that hold regardless of the time difference. The findings reveal the dominance of the Time-length barrier type in the Finnish discussion forum dataset and import vs export tariff discrepancy and product requirement barrier types in the Russian forum dataset. The developed framework can serve as a tool to assist companies or regulators in providing business-related recommendations to overcome the detected trade barriers.