Review of Computer Engineering Research

Comparative analysis of machine and deep learning models with text embeddings for sentiment analysis

2026-01-15T07:45:29-06:00

This study presents a comprehensive comparative evaluation of traditional machine learning (ML) algorithms Naïve Bayes, Random Forest, and Support Vector Machine (SVM) against a deep learning model, Long Short-Term Memory (LSTM), using three distinct text embedding techniques: Term Frequency-Inverse Document Frequency (TF-IDF), FastText, and Word2Vec. A dataset comprising 30,001 social media posts was employed to assess performance across multiple evaluation metrics, including accuracy, precision, recall, F1-score, ROC-AUC, and log loss. Experimental findings reveal that the combination of LSTM with Word2Vec embeddings achieves superior performance, recording an accuracy of 92.65%, an F1-score of 94.37%, a ROC-AUC of 95.70%, and the lowest log loss value of 0.2074. Among the classical machine learning models, Random Forest emerged as the most effective, outperforming Naïve Bayes and SVM in terms of balanced accuracy and generalization capability. The results underscore the pivotal influence of embedding representation in sentiment analysis and demonstrate that deep learning models, when integrated with semantically rich embeddings, can effectively capture contextual dependencies within textual data. The study thus provides valuable insights into developing robust sentiment analysis frameworks and recommends future exploration of hybrid and ensemble learning approaches to enhance generalization and interpretability in real-world natural language processing applications.

The role of artificial intelligence in developing engineering project management

2026-02-02T11:36:20-06:00

This study aims to verify the role of artificial intelligence in developing engineering project management. It seeks to determine the feasibility of implementing artificial intelligence to increase productivity, improve safety, reduce costs, and save time within engineering projects. The focus of the study is on two approaches to project management: traditional, which does not involve extensive integration of the latest intelligent systems, and innovative, where artificial intelligence is used for automated decision-making and risk forecasting. The methodological tools include pairwise comparison methods based on the Saati scale, as well as formulas for integral assessment, which compare the total benefits and opportunities with costs and risks. The results indicate that the innovative approach with deep integration of artificial intelligence has a higher overall indicator due to better productivity, more efficient resource allocation, and a more flexible security system, despite the additional initial costs and risks of implementation. In the long term, this approach allows for significant time savings and improved economic performance, which is critically important in the context of global competition and rapid technological change. This study confirms the feasibility of using artificial intelligence and provides an analytical tool for rational decision-making between traditional and innovative approaches to engineering project management.

Intelligent solar energy forecasting for smart grids using KARN–EWOA within 6G-enabled IoT frameworks

2026-02-17T00:52:55-06:00

Rapid urbanization and rising energy demands make sustainable energy management essential for future smart cities. This study aims to improve solar energy forecasting and smart grid efficiency by tackling issues like data inconsistencies, model optimization, and prediction accuracy. The proposed solution, titled 'Advancing Sustainable Urban Development through Intelligent Energy Management in Smart Grids,' leverages 6G IoT and Artificial Intelligence to enhance energy systems in Next-Generation Smart Cities (EMSG-KARN). This study aims to contribute to the Sustainable Development Goal (SDG) for energy, aligning with the national priority area of energy. Input data from Solar Power Generation and Weather Sensor datasets undergo pre-processing using the Adaptive Resilience Navigation Filter for cleaning and normalization. The processed data is then fed into the Kolmogorov–Arnold Recurrent Network (KARN) to predict solar energy production. Results show that EMSG-KARN achieves superior predictive performance, with 98% accuracy, 97% precision, 98.5% recall, and an F1-score of 96.5%, indicating significant improvements over traditional models. Ablation and cross-validation analyses confirm the contribution of each module, ensuring reliable and scalable solar energy forecasting. This framework provides urban energy planners with a robust, high-performing solution for integrating renewable energy sources, optimizing energy distribution, and improving grid efficiency. The proposed method supports sustainable urban development, climate goals, and offers a scalable, reliable approach for intelligent energy management in smart cities, bridging gaps left by existing AI-based techniques.

Optimizing deep learning models for facial emotion recognition in embedded systems

2026-02-23T00:17:35-06:00

Facial emotion recognition (FER) enables intelligent systems to interpret human affect from facial expressions and is increasingly important for human–computer interaction in resource-constrained environments. This work aims to design and evaluate a real-time FER framework that improves recognition accuracy while maintaining low computational complexity, making it suitable for embedded and edge devices. The proposed approach is developed using transfer learning with deep convolutional neural networks, where MobileNetV2 and ResNet50 are implemented as benchmark models, and EfficientNetB0 is selected as the primary model for optimization. Experiments are conducted on the FER-2013 dataset for both training and evaluation, and the input images are preprocessed to enhance facial feature representation. Fine-tuning is performed on the pretrained networks to reduce training time and improve generalization, while preserving real-time feasibility through lightweight inference. The experimental results show that EfficientNetB0 achieves an accuracy of 72.3% with low-latency performance appropriate for real-time operation. ResNet50 provides comparatively higher accuracy but demands greater computational resources, whereas MobileNetV2 offers a more balanced trade-off between speed and recognition performance. These findings indicate that EfficientNetB0 is a practical solution for real-time FER systems, supporting deployment in embedded platforms and applications such as assistive technologies, smart monitoring, and interactive systems where computational efficiency is critical.

Deepfake video detection using a PSO-optimized Efficientnet-B4 and LSTM hybrid framework

2026-02-23T01:40:26-06:00

Recent advances in deepfake generation technologies have made it possible to generate synthetic videos of unprecedented quality with relatively limited effort, raising serious concerns for digital security, media authenticity, and misinformation. This paper presents a hybrid architecture that combines EfficientNet-B4 to extract high-quality spatial features and Long Short-Term Memory (LSTM) networks for modeling the temporal sequence. Moreover, Particle Swarm Optimization (PSO) is utilized within the training framework to automatically adjust important hyperparameters such as learning rate and LSTM hidden layer units, leading to convergence stability and improved detection performance. The model is trained and tested on the FaceForensics++ (FF++) dataset, which contains 6,450 videos with both real and fake data. Experimental results show that the baseline EfficientNet-B4+LSTM model achieves an accuracy of 86.51%, with precision and recall at 85.28% and 73.87%, respectively. After hyperparameter optimization with PSO, performance improves significantly to 90.91% accuracy, 86.98% precision, and 81.23% recall. A comparative study with re-implemented baseline models, RNN+LSTM and ResNet-50+LSTM, further verifies the superiority of the proposed hybrid method. The results demonstrate the effectiveness of integrating optimized spatial-temporal learning for deepfake detection. Practically, the proposed framework is envisioned to provide a reliable solution for digital forensics, cybersecurity, and media authentication systems, with strong potential for deployment in real-world content verification applications.