Palak Bari, Gurnur Bedi, Khushi Joshi, Anupama Jawale^*

Journal on Artificial Intelligence, Vol.7, pp. 499-508, 2025, DOI:10.32604/jai.2025.072531 - 17 November 2025

Abstract This study investigates sarcasm detection in text using a dataset of 8095 sentences compiled from MUStARD and HuggingFace repositories, balanced across sarcastic and non-sarcastic classes. A sequential baseline model (LSTM) is compared with transformer-based models (RoBERTa and XLNet), integrated with attention mechanisms. Transformers were chosen for their proven ability to capture long-range contextual dependencies, whereas LSTM serves as a traditional benchmark for sequential modeling. Experimental results show that RoBERTa achieves 0.87 accuracy, XLNet 0.83, and LSTM 0.52. These findings confirm that transformer architectures significantly outperform recurrent models in sarcasm detection. Future work will incorporate multimodal More >

Yanfeng Li¹, Dongxu Han^1,*, Jinhui Lin², Qingwei Zhai³, Xiaohua Wu¹

The International Conference on Computational & Experimental Engineering and Sciences, Vol.33, No.2, pp. 1-1, 2025, DOI:10.32604/icces.2025.011547

Abstract Liquid hydrogen (LH2), with its high volumetric energy density and high purity, has become a promising choice for hydrogen storage. As the demand for hydrogen as a clean energy source continues to grow, the importance of liquid hydrogen in energy storage is becoming increasingly significant. However, the safe operation and storage of liquid hydrogen face several challenges, particularly the self-pressurization process within storage tanks. During storage, heat ingress into the tank causes the evaporation of liquid hydrogen, leading to a continuous rise in vapor pressure, resulting in self-pressurization. Accurately predicting this process is crucial for… More >

Sarab Almuhaideb^1,*, Najwa Altwaijry¹, Isra Al-Turaiki¹, Ahmad Raza Khan², Hamza Ali Rizvi³

CMC-Computers, Materials & Continua, Vol.85, No.2, pp. 3095-3128, 2025, DOI:10.32604/cmc.2025.067390 - 23 September 2025

Abstract Many bioinformatics applications require determining the class of a newly sequenced Deoxyribonucleic acid (DNA) sequence, making DNA sequence classification an integral step in performing bioinformatics analysis, where large biomedical datasets are transformed into valuable knowledge. Existing methods rely on a feature extraction step and suffer from high computational time requirements. In contrast, newer approaches leveraging deep learning have shown significant promise in enhancing accuracy and efficiency. In this paper, we investigate the performance of various deep learning architectures: Convolutional Neural Network (CNN), CNN-Long Short-Term Memory (CNN-LSTM), CNN-Bidirectional Long Short-Term Memory (CNN-BiLSTM), Residual Network (ResNet), and… More >

Abubakar Elsafi^*

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.2, pp. 1749-1766, 2025, DOI:10.32604/cmes.2025.066449 - 31 August 2025

Abstract Domain randomization is a widely adopted technique in deep reinforcement learning (DRL) to improve agent generalization by exposing policies to diverse environmental conditions. This paper investigates the impact of different reset strategies, normal, non-randomized, and randomized, on agent performance using the Deep Deterministic Policy Gradient (DDPG) and Twin Delayed DDPG (TD3) algorithms within the CarRacing-v2 environment. Two experimental setups were conducted: an extended training regime with DDPG for 1000 steps per episode across 1000 episodes, and a fast execution setup comparing DDPG and TD3 for 30 episodes with 50 steps per episode under constrained computational… More >

KL Vasudev¹, Manish Pandey², Jaan H. Pu^3,*

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.7, pp. 1545-1569, 2025, DOI:10.32604/fdmp.2025.065289 - 31 July 2025

Abstract This study presents a comparative analysis of optimisation strategies for designing hull shapes of Autonomous Underwater Vehicles (AUVs), paying special attention to drag, lift-to-drag ratio, and delivered power. A fully integrated optimisation framework is developed accordingly, combining a single-objective Genetic Algorithm (GA) for design parameter generation, Computer-Aided Geometric Design (CAGD) for the creation of hull geometries and associated fluid domains, and a Reynolds-Averaged Navier–Stokes (RANS) solver for evaluating hydrodynamic performance metrics. This unified approach eliminates manual intervention, enabling automated determination of optimal hull configurations. Three distinct optimisation problems are addressed using the proposed methodology. First,… More >

Haniif Prasetiawan^1,2,*, Dewi Selvia Fardhyanti¹, Hadiyanto², Widya Fatriasari³

Journal of Renewable Materials, Vol.13, No.7, pp. 1347-1366, 2025, DOI:10.32604/jrm.2025.02024-0070 - 22 July 2025

Abstract Bio-oil is a renewable fuel that can be obtained from biomass waste, such as empty palm fruit bunches, sugarcane bagasse, and rice husks. Within a biorefinery framework, bio-oil had not met the standards as a fuel due to the presence of impurities like corrosive phenol. Therefore, the separation of phenol from bio-oil is essential and can be achieved using the extraction method. In this study, biomass wastes (empty fruit bunches of oil palm, sugarcane bagasse, and rice husk) were pyrolyzed in a biorefinery framework to produce bio-oil, which was then refined through liquid-liquid extraction with… More >

Issah Zabsonre Alhassan^1,2,*, Gaddafi Abdul-Salaam¹, Michael Asante¹, Yaw Marfo Missah¹, Alimatu Sadia Shirazu¹

Journal of Cyber Security, Vol.7, pp. 165-196, 2025, DOI:10.32604/jcs.2025.063529 - 07 July 2025

Abstract Pseudorandom number generators (PRNGs) are foundational to modern cryptography, yet existing approaches face critical trade-offs between cryptographic security, computational efficiency, and adaptability to emerging threats. Traditional PRNGs (e.g., Mersenne Twister, LCG) remain widely used in low-security applications despite vulnerabilities to predictability attacks, while machine learning (ML)-driven and chaos-based alternatives struggle to balance statistical robustness with practical deployability. This study systematically evaluates traditional, chaos-based, and ML-driven PRNGs to identify design principles for next-generation systems capable of meeting the demands of high-security environment like blockchain and IoT. Using a framework that quantifies cryptographic robustness (via NIST SP… More >

Mohammed Salam Abdl Ghafoor, Mohammed K. Al-Saadi, Ameer Abed Jaddoa^*

Frontiers in Heat and Mass Transfer, Vol.23, No.3, pp. 975-990, 2025, DOI:10.32604/fhmt.2025.064025 - 30 June 2025

Abstract The comparison of experimental performance was studied for soda cans: longitudinal, transverse, diagonal, and smooth cases to improve the heat transfer rate and thermal performance of the solar air heater, in this study using a frame which has 1.5 m × 0.5 m × 0.05 m dimensions, the arrangements were placed on the absorber plate inside the channel, raising the air’s exit temperature as it passed by. The work was carried out for 4 cases in January in Baghdad, Iraq, under specific conditions to compare them to reach the ideal case and the best performance… More >

Duy Dao¹, Hervé Kerivin², Philippe Lacomme^2,*, Bogdan Vulpescu³

Journal of Quantum Computing, Vol.7, pp. 39-54, 2025, DOI:10.32604/jqc.2025.064764 - 30 May 2025

Abstract Track finding is a complex optimization problem, originally introduced in particle physics for the reconstruction of the trajectories of particles. A track is typically composed of several consecutive segments, which together form a smooth curve without any bifurcations. In this paper, we investigate various modeling approaches to assess their effectiveness and impact when applied to track finding, using both quantum and classical methods. We present implementations of three classical models using CPLEX, two quantum models on actual D-Wave quantum computers, and one quantum model on a D-Wave simulator. The results show that, while CPLEX provides… More >

Yong Zheng^*

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 4315-4328, 2025, DOI:10.32604/cmc.2025.063498 - 19 May 2025

Abstract A recommender system is a tool designed to suggest relevant items to users based on their preferences and behaviors. Collaborative filtering, a popular technique within recommender systems, predicts user interests by analyzing patterns in interactions and similarities between users, leveraging past behavior data to make personalized recommendations. Despite its popularity, collaborative filtering faces notable challenges, and one of them is the issue of grey-sheep users who have unusual tastes in the system. Surprisingly, existing research has not extensively explored outlier detection techniques to address the grey-sheep problem. To fill this research gap, this study conducts… More >