Dialogue State Tracking (DST) is a critical component of task-oriented spoken dialogue systems (SDS), tasked with maintaining an accurate representation of the conversational state by predicting slots and their corresponding values. Recent advances leverage Large Language Models (LLMs) with prompt-based tuning to improve tracking accuracy and efficiency. However, these approaches often incur substantial computational and memory overheads and typically address slot extraction implicitly within prompts, without explicitly modeling the complex dependencies between slots and values. In this work, we propose PUGG, a novel DST framework that constructs schema-driven prompts to fine-tune GPT-2 and utilizes its tokenizer to implement a memory encoder. PUGG explicitly extracts slot values via GPT-2 and employs Graph Attention Networks (GATs) to model and reason over the intricate relationships between slots and their associated values. We evaluate PUGG on four publicly available datasets, where it achieves state-of-the-art performance across multiple evaluation metrics, highlighting its robustness and generalizability in diverse conversational scenarios. Our results indicate that the integration of GPT-2 substantially reduces model complexity and memory consumption by streamlining key processes. Moreover, prompt tuning enhances the model’s flexibility and precision in extracting relevant slot-value pairs, while the incorporation of GATs facilitates effective relational reasoning, leading to improved dialogue state representations.

As legal cases grow in complexity and volume worldwide, integrating machine learning and artificial intelligence into judicial systems has become a pivotal research focus. This study introduces a comprehensive framework for verdict recommendation that synergizes rule-based methods with deep learning techniques specifically tailored to the legal domain. The proposed framework comprises three core modules: legal feature extraction, semantic similarity assessment, and verdict recommendation. For legal feature extraction, a rule-based approach leverages Black’s Law Dictionary and WordNet Synsets to construct feature vectors from judicial texts. Semantic similarity between cases is evaluated using a hybrid method that combines rule-based logic with an LSTM model, analyzing the feature vectors of query cases against a legal knowledge base. Verdicts are then recommended through a rule-based retrieval system, enhanced by predefined legal statutes and regulations. By merging rule-based methodologies with deep learning, this framework addresses the interpretability challenges often associated with contemporary AI models, thereby enhancing both transparency and generalizability across diverse legal contexts. The system was rigorously tested using a legal corpus of 43,000 case laws across six categories: Criminal, Revenue, Service, Corporate, Constitutional, and Civil law, ensuring its adaptability across a wide range of judicial scenarios. Performance evaluation showed that the feature extraction module achieved an average accuracy of 91.6% with an F-Score of 95%. The semantic similarity module, tested using Manhattan, Euclidean, and Cosine distance metrics, achieved 88% accuracy and a 93% F-Score for short queries (Manhattan), 89% accuracy and a 93.7% F-Score for medium-length queries (Euclidean), and 87% accuracy with a 92.5% F-Score for longer queries (Cosine). The verdict recommendation module outperformed existing methods, achieving 90% accuracy and a 93.75% F-Score. This study highlights the potential of hybrid AI frameworks to improve judicial decision-making and streamline legal processes, offering a robust, interpretable, and adaptable solution for the evolving demands of modern legal systems.

Identifying druggable proteins, which are capable of binding therapeutic compounds, remains a critical and resource-intensive challenge in drug discovery. To address this, we propose CEL-IDP (Comparison of Ensemble Learning Methods for Identification of Druggable Proteins), a computational framework combining three feature extraction methods Dipeptide Deviation from Expected Mean (DDE), Enhanced Amino Acid Composition (EAAC), and Enhanced Grouped Amino Acid Composition (EGAAC) with ensemble learning strategies (Bagging, Boosting, Stacking) to classify druggable proteins from sequence data. DDE captures dipeptide frequency deviations, EAAC encodes positional amino acid information, and EGAAC groups residues by physicochemical properties to generate discriminative feature vectors. These features were analyzed using ensemble models to overcome the limitations of single classifiers. EGAAC outperformed DDE and EAAC, with Random Forest (Bagging) and XGBoost (Boosting) achieving the highest accuracy of 71.66%, demonstrating superior performance in capturing critical biochemical patterns. Stacking showed intermediate results (68.33%), while EAAC and DDE-based models yielded lower accuracies (56.66%–66.87%). CEL-IDP streamlines large-scale druggability prediction, reduces reliance on costly experimental screening, and aligns with global initiatives like Target 2035 to expand action-able drug targets. This work advances machine learning-driven drug discovery by systematizing feature engineering and ensemble model optimization, providing a scalable workflow to accelerate target identification and validation.

In this paper, we investigated the complex dynamics of a discrete-time predator-prey model incorporating a double Allee effect in the prey population. We investigated the existence and stability of biologically meaningful fixed points, including extinction, prey-only, and coexistence equilibria. Through analytical and numerical bifurcation analysis, we demonstrated that the model underwent a Neimark-Sacker bifurcation as key parameters varied, leading to quasi-periodic oscillations that characterized realistic population cycles. Our results revealed that stronger Allee effects tend to destabilize the model, increasing extinction risks and promoting oscillatory dynamics, while higher predator mortality rates and saturation in predation response enhance stability. A comparative analysis with models lacking the Allee effect highlights its critical role in delaying equilibrium convergence and inducing instability at low population densities. These findings provide important insights for ecological conservation, particularly for species vulnerable to population depletion, and contribute to the theoretical understanding of predator-prey models with density-dependent growth constraints.

This paper explores the dynamics of a fractional prey–predator system with a ratio-dependent functional response with memory and hereditary effects in predator–prey interactions. The model is developed by the Caputo fractional derivative, and the existence, uniqueness, positivity, and boundedness of solutions are proven to satisfy biological reality. Stability conditions for local and global stability of both predator-free and coexistence equilibria are proven through linearization and Lyapunov function techniques. The fractional order is used as a bifurcation parameter, and the appearance of Hopf bifurcations is analytically explained with demonstration of the influence of memory on oscillations. To examine discrete-time dynamics, the piecewise constant argument is used to derive a discrete counterpart of the fractional model. The discrete model indicates a wide range of rich complex oscillatory phenomena, including period-doubling and Neimark–Sacker bifurcations, leading to periodic, quasiperiodic, and chaotic oscillations. Numerical computations, including bifurcation diagrams, phase portraits, and Lyapunov exponents, verify the analytical results and describe the routes of transition to chaos. A comparative analysis to compare integer- and fractional-order cases indicates that memory effects enhance dynamical richness and sensitivity to parameters. The study provides a unified framework relating continuous fractional dynamics and their discrete implementations and provides additional insight into how memory and discretization interact to modify stability and bifurcation in ecological models.

Leaf disease identification is one of the most promising applications of convolutional neural networks (CNNs). This method represents a significant step towards revolutionizing agriculture by enabling the quick and accurate assessment of plant health. In this study, a CNN model was specifically designed and tested to detect and categorize diseases on fig tree leaves. The researchers utilized a dataset of 3422 images, divided into four classes: healthy, fig rust, fig mosaic, and anthracnose. These diseases can significantly reduce the yield and quality of fig tree fruit. The objective of this research is to develop a CNN that can identify and categorize diseases in fig tree leaves. The data for this study was collected from gardens in the Amandi and Mamash Khail Bannu districts of the Khyber Pakhtunkhwa region in Pakistan. To minimize the risk of overfitting and enhance the model’s performance, early stopping techniques and data augmentation were employed. As a result, the model achieved a training accuracy of 91.53% and a validation accuracy of 90.12%, which are considered respectable. This comprehensive model assists farmers in the early identification and categorization of fig tree leaf diseases. Our experts believe that CNNs could serve as valuable tools for accurate disease classification and detection in precision agriculture. We recommend further research to explore additional data sources and more advanced neural networks to improve the model’s accuracy and applicability. Future research will focus on expanding the dataset by including new diseases and testing the model in real-world scenarios to enhance sustainable farming practices.