Accelerating materials property prediction via a hybrid Transformer Graph framework that leverages four body interactions by Mohammad Madani, Valentina Lacivita, Yongwoo Shin, Anna Tarakanova

“…It outperforms state-of-the-art models in 8 materials property regression tasks. …”
Get full text

Secured DICOM medical image transition with optimized chaos method for encryption and customized deep learning model for watermarking by R. Abirami, C. Malathy

“…In comparison to the state-of-the-art model, the suggested model performs better in every respect. …”
Get full text

ViT-DualAtt: An efficient pornographic image classification method based on Vision Transformer with dual attention by Zengyu Cai, Liusen Xu, Jianwei Zhang, Yuan Feng, Liang Zhu, Fangmei Liu

“…Our results demonstrated that ViT-DualAtt achieved a classification accuracy of 97.2% ± 0.1% in pornographic image classification tasks, outperforming the current state-of-the-art model (RepVGG-SimAM) by 2.7%. Furthermore, the model achieves a pornographic image miss rate of only 1.6%, significantly reducing the risk of pornographic image dissemination on internet platforms.…”
Get full text

Attention-enhanced corn disease diagnosis using few-shot learning and VGG16 by Ruchi Rani, Jayakrushna Sahoo, Sivaiah Bellamkonda, Sumit Kumar

“…Thus, Few Shot Learning is the state-of-the-art model in machine learning, which requires minimum examples to train the model for generalization. …”
Get full text

Dual intent view contrastive learning for knowledge aware recommender systems by Jianhua Guo, Zhixiang Yin, Shuyang Feng, Donglin Yao, Shaopeng Liu

“…Experimental results on three benchmark datasets demonstrate that DIVCL outperforms state-of-the-art models, showcasing its superior performance. The implementation is available at: https://github.com/yzxx667/DIVCL .…”
Get full text

Unified Quantile Regression Deep Neural Network with Time-Cognition for Probabilistic Residential Load Forecasting by Zhuofu Deng, Binbin Wang, Heng Guo, Chengwei Chai, Yanze Wang, Zhiliang Zhu

“…With ablation experiments, the proposed model achieved the best results in the AQS, AACE, and inversion error, and especially the average of the AACE is grown by 34.71%, 75.22%, and 32.44% compared with QGBRT, QCNN, and QLSTM, respectively, indicating that our method has excellent reliability and robustness rather than the state-of-the-art models obviously. Meanwhile, great performances of efficient time response demonstrate that our proposed work has promising prospects in practical applications.…”
Get full text

Future increase in compound soil drought-heat extremes exacerbated by vegetation greening by Jun Li, Yao Zhang, Emanuele Bevacqua, Jakob Zscheischler, Trevor F. Keenan, Xu Lian, Sha Zhou, Hongying Zhang, Mingzhu He, Shilong Piao

“…Here, using a suite of state-of-the-art model simulations, we show that the projected vegetation greening will increase the frequency of global compound soil drought-heat events, equivalent to 12–21% of the total increment at the end of 21st century. …”
Get full text

Combining Region-Guided Attention and Attribute Prediction for Thangka Image Captioning Method by Fujun Zhang, Wendong Kang, Wenjin Hu

“…On the COCO dataset in the natural domain, RGFEAP achieves performance comparable to other state-of-the-art models, showcasing its strong adaptability.…”
Get full text

Attention-Aware Heterogeneous Graph Neural Network by Jintao Zhang, Quan Xu

“…Experimental results on three widely used datasets showed that the AHNN model could significantly outperform the state-of-the-art models.…”
Get full text

Decomposition-Based Multistep Sea Wind Speed Forecasting Using Stacked Gated Recurrent Unit Improved by Residual Connections by Jupeng Xie, Huajun Zhang, Linfan Liu, Mengchuan Li, Yixin Su

“…The experiment results on three different sea areas show that the performance of this model surpasses those of a state-of-the-art model, several benchmarks, and decomposition-based models.…”
Get full text

Low-Rank Adaptation of Pre-Trained Large Vision Models for Improved Lung Nodule Malignancy Classification by Benjamin P. Veasey, Amir A. Amini

“…<italic>Results:</italic> The best LoRA-adapted model achieved a 3&#x0025; increase in ROC AUC over the state-of-the-art model, utilized 89.9&#x0025; fewer parameters, and reduced training times by 36.5&#x0025;. …”
Get full text

Multimodal Autism Spectrum Disorder Method Using GCN With Dual Transformers by Tianming Song, Zhe Ren, Jian Zhang, Yawei Qu, Yingying Cui, Zhengda Liang

“…The experimental results reveal that our approach significantly outperforms existing baseline and state-of-the-art models. The method achieves 79.47% of accuracy, 78.97% precision, 82.11% recall, and 0.85 of AUC metrics. …”
Get full text

Enhancing zero-shot stance detection via multi-task fine-tuning with debate data and knowledge augmentation by Qinlong Fan, Jicang Lu, Yepeng Sun, Qiankun Pi, Shouxin Shang

“…Our model outperforms current state-of-the-art models on these two datasets, demonstrating the superiority of multi-task fine-tuning with debate data and knowledge augmentation.…”
Get full text

Accessible AI Diagnostics and Lightweight Brain Tumor Detection on Medical Edge Devices by Akmalbek Abdusalomov, Sanjar Mirzakhalilov, Sabina Umirzakova, Abror Shavkatovich Buriboev, Azizjon Meliboev, Bahodir Muminov, Heung Seok Jeon

“…The modified RetinaNet achieves an average precision (AP) of 32.1, surpassing state-of-the-art models in small tumor detection (AP_S: 14.3) and large tumor localization (AP_L: 49.7). …”
Get full text

Masked and unmasked Face Recognition Model Using Deep Learning Techniques. A case of Black Race. by Mabiriz,I, Vicent, Ampaire, Ray Brooks, Muhoza, B. Gloria

“…However, the state-of-the-art models are not generalizable across populations and probably will not work in the Ugandan context because they have not been implemented with capabilities to eliminate racial discrimination in face recognition. …”
Get full text

InfectA-Chat, an Arabic Large Language Model for Infectious Diseases: Comparative Analysis by Yesim Selcuk, Eunhui Kim, Insung Ahn

“…Among the state-of-the-art models, InfectA-Chat achieved a leading performance of 23.78%, competing closely with the GPT-4 model. …”
Get full text

A Hybrid Transformer Architecture for Multiclass Mental Illness Prediction Using Social Media Text by Adnan Karamat, Muhammad Imran, Muhammad Usman Yaseen, Rasool Bukhsh, Sheraz Aslam, Nouman Ashraf

“…The results reveal outstanding performance of the proposed architecture with an overall accuracy of 92% and an F1-score of 92%, surpassing state-of-the-art models in comparison. This study underscores the necessity for further research in this field and illustrates the potential of advanced technologies to address mental health issues in contemporary society.…”
Get full text

Edge-centric optimization: a novel strategy for minimizing information loss in graph-to-text generation by Zheng Yao, Jingyuan Li, Jianhe Cen, Shiqi Sun, Dahu Yin, Yuanzhuo Wang

“…Experimental results reveal that TriELMR exhibits exceptional performance across various benchmark tests, especially on the webnlgv2.0 and Event Narrative datasets, achieving BLEU-4 scores of $$66.5\%$$ 66.5 % and $$37.27\%$$ 37.27 % , respectively, surpassing the state-of-the-art models. These demonstrate the advantages of TriELMR in maintaining the accuracy of graph structural information. …”
Get full text

Enhanced CATBraTS for Brain Tumour Semantic Segmentation by Rim El Badaoui, Ester Bonmati Coll, Alexandra Psarrou, Hykoush A. Asaturyan, Barbara Villarini

“…Through the adoption of E-CATBraTS, the accuracy of the results improved significantly on two datasets, outperforming the current state-of-the-art models by a mean DSC of 2.6% while maintaining a high accuracy that is comparable to the top-performing models on the other datasets. …”
Get full text

Hybrid generative adversarial network based on frequency and spatial domain for histopathological image synthesis by Qifeng Liu, Tao Zhou, Chi Cheng, Jin Ma, Marzia Hoque Tania

“…Experiments on the Patch Camelyon dataset show superior performance over eight state-of-the-art models across five metrics. This approach advances automated histopathological image generation with potential for clinical applications.…”
Get full text