Automated Essay Scoring (AES) systems face persistent challenges in delivering accuracy and efficiency in evaluations. This study introduces an approach that combines embeddings generated using RoBERTa with handcrafted linguistic features, leveraging Lightweight XGBoost (LwXGBoost) for enhanced scoring precision. The embeddings capture the contextual and semantic aspects of essay content, while handcrafted features incorporate domain-specific attributes such as grammar errors, readability, and sentence length. This hybrid feature set allows LwXGBoost to handle high-dimensional data and model intricate feature interactions effectively. Our experiments on a diverse AES dataset, consisting of essays from students across various educational levels, yielded a QWK score of 0.941. This result demonstrates the superior scoring accuracy and the model’s robustness against noisy and sparse data. The research underscores the potential for integrating embeddings with traditional handcrafted features to improve automated assessment systems.

Algorithmic stock trading has improved tremendously, with Reinforcement Learning (RL) algorithms being more adaptable than classic approaches like mean reversion and momentum. However, challenges remain in adequately depicting market events and generating suitable rewards to influence the trading decisions of an agent in a dynamic environment. This study proposed an improved stock market trading framework termed the RMS-Driven Deep Reinforcement Learning (DRL) model for optimal portfolio management. The research attempts to give a more comprehensive view of the market and, as a result, enhance trading decisions by including consumer information and incorporating news sentiments into the model, in addition to data from typical earnings reports. More specifically, three kinds of DRL models are presented, combined with data from stock earnings reports, Max Drawdown rewards, and sentiment indicators (RMS), known as PPO_RMS, A2C_RMS, and DDPG_RMS, respectively. The findings of this research indicate that the integrated model, mainly the DDPG_RMS effectively outperforms the baseline ^DJI index in many risk-return analyses in ratios showing better risk management, and profitability. The proposed stock trading model generates a maximum cumulative return of 27% with a Sharpe ratio of 0.66, showing an appropriate trade-off between risk and return. This approach, which incorporates sentiment analysis and Max Drawdown rewards, significantly enhances the model’s performance in adapting to changing market conditions. Therefore, the results emphasize the appropriateness of integrating sentiment indices with traditional financial data to enhance a trader’s performance while also offering essential information to aid in the development of improved trading tactics in continuously changing financial markets.

Breast cancer, a widespread malignancy predominantly affecting women aged 40 and above, presents a significant global health challenge with high mortality rates. The scarcity of medical data underscores the need for collaborative efforts among hospitals to enhance automated breast cancer detection. This research employs decentralized Federated Learning (FL) to facilitate cooperative learning across an interconnected smart hospital network, addressing data privacy, regulatory compliance, voluminous medical image data, and the necessity for distributed machine learning. Our innovative approach integrates Ant Colony Optimization (ACO) for hyperparameter fine-tuning and Neural Architecture Search (NAS) in a collaborative framework for smart hospitals linked with decentralized edge intelligent networks. This optimization strategy significantly improves the performance of our breast cancer detection system. Through a comprehensive experimental study (including diverse datasets), we classify Normal vs. Mass and Benign vs. Malignant regions in mammograms within a decentralized, federated collaborative learning environment. Empirical results consistently highlight the superiority of models trained using our method over individual hospital client-level training. Our method yielded significant improvements across evaluation measures: for Normal vs. Mass, achieving 92.6% sensitivity, 93.0% specificity, and 93.0% accuracy; for Benign vs. Malignant, achieving 89.6% sensitivity, 91.6% specificity, and 89.7% accuracy. Moreover, it has obtained a 6% and 5% increase in accuracy for Normal vs. Mass and Benign vs. Malignant cases, respectively, compared to the PSO-based HPO method. This evidence underscores the potential of collaborative approaches, emphasizing decentralized FL as a robust paradigm in medical research. The incorporation of ACO optimization reinforces the effectiveness of the proposed computer-aided diagnosis (CAD) system, marking a noteworthy advancement in the ongoing fight against breast cancer.

This research introduces an innovative approach for identifying duplicate questions within the Stack Overflow community, a challenging task in natural language processing. Leveraging deep learning techniques, our proposed methodology combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to capture both local and long-term dependencies in textual data. We employ word embeddings, specifically Google’s Word2Vec and GloVe, to enhance text representation. Extensive experiments on the Stack Overflow dataset demonstrate the effectiveness of our approach, achieving an impressive accuracy of 87.09% and a recall rate of 87.%. The integration of CNN and LSTM models significantly streamlines preprocessing, making it a valuable tool for detecting duplicate questions. Future directions include extending the model to multiple languages and exploring alternative word embedding techniques. Our approach presents promising applications beyond Stack Overflow, offering solutions for identifying similar questions on various question-and-answer platforms.

The global prevalence of obesity presents a pressing challenge to public health and healthcare systems, necessitating accurate prediction and understanding for effective prevention and management strategies. This article addresses the need for improved obesity prediction models by conducting a comprehensive analysis of existing machine learning (ML) and deep learning (DL) approaches. This study introduces a novel hybrid model, Attention-based Bi-LSTM (ABi-LSTM), which integrates attention mechanisms with bidirectional Long Short-Term Memory (Bi-LSTM) networks to enhance interpretability and performance in obesity prediction. Our study fills a crucial gap by bridging healthcare and urban planning domains, offering insights into data-driven approaches to promote healthier living within urban environments. The proposed ABi-LSTM model demonstrates exceptional performance, achieving a remarkable accuracy of 96.5% in predicting obesity levels. Comparative analysis showcases its superiority over conventional approaches, with superior precision, recall, and overall classification balance. This study highlights significant advancements in predictive accuracy and positions the ABi-LSTM model as a pioneering solution for accurate obesity prognosis. The implications extend beyond healthcare, offering a precise tool to address the global obesity epidemic and foster sustainable development in smart cities.