Drug-Gene Interaction Prediction Method through Cross Granularity Subgraph Contrastive Learning and Attention Mechanism Fusion by HU Dongdong, PENG Yang, TAN Shuqiu, ZHU Xiaofei

“…[Findings] The experimental results on two real datasets show that compared with the baseline; the proposed model has better classification performance.…”
Get full text

AI-driven video summarization for optimizing content retrieval and management through deep learning techniques by Deepali Vora, Payal Kadam, Dadaso D Mohite, Nilesh Kumar, Nimit Kumar, Pratheeik Radhakrishnan, Shalmali Bhagwat

“…The framework achieves precision, recall, and F-score of 79.2%, 86.5%, and 83%, respectively, on the YouTube, EPFL, and TVSum datasets. Beyond technological advancements, opportunities for effective content management are highlighted, emphasizing the promotion of sustainable digital practices. …”
Get full text

Continuum and Soft Robots in Minimally Invasive Surgery: A Systematic Review by Fahad Iqbal, Mojtaba Esfandiari, Golchehr Amirkhani, Hamidreza Hoshyarmanesh, Sanju Lama, Mahdi Tavakoli, Garnette R. Sutherland

“…In this review, we first highlight recent developments in mechanical-continuum robots for traditional minimally invasive surgery and then summarize the current state-of-the-art in steerable catheter-based interventions. We discuss limitations to current approaches and explore the emerging potential of soft robots as a novel strategy to address the challenge of developing versatile, highly articulated flexible tools for minimally invasive surgical interventions. …”
Get full text

Research on Wood Defects Feature Imbalance Optimization and Recognition by Xiao Wang

“…Besides, generalization ability test indicates that new methods allow the classifier to have comparable accuracies on five additional datasets. The proposed loss functions improve the model performance through optimizing the model training process, providing a new idea for deep learning application in wood defects detection.…”
Get full text

Leveraging multiplexed metasurfaces for multi-task learning with all-optical diffractive processors by Behroozinia Sahar, Gu Qing

“…In this work, we utilize the polarization and wavelength degrees of freedom of light to achieve optical multi-task identification using the MNIST, FMNIST, and KMNIST datasets. Employing bilayer cascaded metasurfaces, we construct dual-channel DNNs capable of simultaneously classifying two tasks, using polarization and wavelength multiplexing schemes through a meta-atom library. …”
Get full text

Multimodal Emotion Recognition: Emotion Classification Through the Integration of EEG and Facial Expressions by Songul Erdem Guler, Fatma Patlar Akbulut

“…The results validate the effectiveness of this approach, demonstrating the high accuracy of the Gated Recurrent Unit (GRU) model, which achieved an average of 91.8% classification accuracy on unimodal (EEG-only) data and an average of 97.8% classification accuracy on multimodal (EEG and facial expressions) datasets in the multi-class emotion categories. The findings emphasize that by applying a multi-class classification framework, multimodal approaches offer significant improvements over traditional unimodal techniques. …”
Get full text

Log-Driven Behavior Discrimination of Process Robots Using Entropy Similarity by Lu Li, Huan Fang

“…Finally, a series of experiments are conducted on a set of publicly available datasets, validating the feasibility, generality, and effectiveness of the proposed method.…”
Get full text

Precision and efficiency in skin cancer segmentation through a dual encoder deep learning model by Asaad Ahmed, Guangmin Sun, Anas Bilal, Yu Li, Shouki A. Ebad

“…To evaluate DuaSkinSeg’s effectiveness, we conducted experiments on three publicly available benchmark datasets: ISIC 2016, ISIC 2017, and ISIC 2018. The results demonstrate that DuaSkinSeg achieves competitive performance compared to existing methods, highlighting the potential of the dual encoder architecture for accurate skin lesion segmentation.…”
Get full text

Manet: motion-aware network for video action recognition by Xiaoyang Li, Wenzhu Yang, Kanglin Wang, Tiebiao Wang, Chen Zhang

“…We conducted extensive experiments on five mainstream datasets, Something-Something V1 & V2, Jester, Diving48, and UCF-101, to validate the effectiveness of MANet. …”
Get full text

Diagnostic classification in toxicologic pathology using attention-guided weak supervision and whole slide image features: a pilot study in rat livers by Philip Zehnder, Jeffrey Feng, Trung Nguyen, Philip Shen, Ruth Sullivan, Reina N. Fuji, Fangyao Hu

“…We propose an innovative weakly supervised learning method that leverages minimal annotations, a state-of-the-art self-supervised vision transformer for embedding extraction, and a novel guided attention mechanism that is better suited for heavily imbalanced datasets typical in toxicologic pathology. Our model demonstrates improvements in diagnostic classification and attention heatmap quality over the previously described clustering-constrained-attention multiple-instance learning method on several lesion classes in rat livers (38% improvement in AUC). …”
Get full text

IAE-CDNet: A Remote Sensing Change Detection Network for Buildings With Interactive Attention-Enhanced by Zhaoyang Han, Linlin Zhang, Qingyan Meng, Chongchang Wang, Wenxu Shi, Maofan Zhao

“…We conduct extensive experiments on three datasets. Results indicate that the evaluation indicators and performance of our IAE-CDNet are better than those of other state-of-the-art methods.…”
Get full text

Balancing between being the most valuable player (MVP) and passing the ball: a qualitative study of support when living with chronic pain in Sweden by Markus Saarijärvi, Sara Wallström, Inger Ekman, Mari Lundberg, Veronica Lilja, Vivi-Anne Segertoft

“…Objective This study aimed to elucidate the meaning of lived experiences of support from social networks and the healthcare sector in persons with chronic pain.Design A qualitative, phenomenological hermeneutic method was used to analyse interview data.Setting Participants were recruited from patient organisations in Sweden.Participants Ten (seven women, two men and one non-binary) individuals with chronic musculoskeletal pain were included.Findings The meaning of lived experiences of support in persons with chronic pain involves balancing between being the most valuable player (MVP) and passing the ball, meaning balancing between being a capable person and accepting support to be that capable person.Conclusion For participants who lived with chronic pain, support means balancing between being capable (the MVP) and willing to accept support (passing the ball), which aligns with the concept of person-centred care. …”
Get full text

Bio-primed machine learning to enhance discovery of relevant biomarkers by David M. Henke, Alexander Renwick, Joseph R. Zoeller, Jitendra K. Meena, Nicholas J. Neill, Elizabeth A. Bowling, Kristen L. Meerbrey, Thomas F. Westbrook, Lukas M. Simon

“…Applying our method to multiple dependency datasets, we identified biomarkers which traditional methods overlooked. …”
Get full text

INTERNATIONALIZATION OF CONFLICT AS A CHALLENGE TO PEACE AND DEVELOPMENT IN AFRICA by ANTHONY IMEH UMOH, BARINAADAA NWINKOL

“…This has made Africa to be christened the hub of conflicts and wars. Most pathetic is the fact that these conflicts and wars have defied any meaningful solution, and their negative impact has impeded peace and development in the continent. …”
Get full text

Sideroflexin family genes were dysregulated and associated with tumor progression in prostate cancers by Hua Huang, Huibo Lian, Wang Liu, Benyi Li, Runzhi Zhu, Haiyan Shao

“…In this study, we took a comprehensive approach to investigate their expression profiles in benign prostate tissue, prostate-derived cell lines, and prostate cancer tissues using multiple transcriptome datasets. Our results showed that SFXN1/3/4 genes were predominantly expressed in prostate tissue and cell lines. …”
Get full text

Applied aspects of modern non-blind image deconvolution methods by O.B. Chaganova, A.S. Grigoryev, D.P. Nikolaev, I.P. Nikolaev

“…We developed a benchmark for validating non-blind deconvolution methods, which includes datasets of ground truth images and blur kernels, as well as a test scheme for assessing restoration quality and error robustness. …”
Get full text

Rural-Urban Disparity in Premature Cancer Mortality in Young People Aged 15–44 Years in China, 2004–2021 by Chunrong Chen, Xing Xing, Shaojie Li, Bo Qu, Chunyu Liu, He Zhu, He Zhu

“…ObjectiveThis study aims to examine and compare premature cancer mortality in young people aged 15–44 years old between rural and urban areas to inform early-onset cancer prevention.MethodsThe data were obtained from the China Death Surveillance Datasets from 2004 to 2021. The study sample consisted of cancer deaths of young people aged 15–44 years old. …”
Get full text

Detection to false data for smart grid by Jian Zheng, Shumiao Ren, Jingyue Zhang, Yu Kui, Jingyi Li, Qin Jiang, Shiyan Wang

“…Finally, experiments on simulated and real datasets indicate that the proposed method obtains 0.9738 detected accuracy, and the sensitivity to false data reaches 0.9387, defeating against the competitors, moreover, the proposed method does not exhibit exponential detection time as data volume augments. …”
Get full text

UniLF: A novel short-term load forecasting model uniformly considering various features from multivariate load data by Shiyang Zhou, Qingyong Zhang, Peng Xiao, Bingrong Xu, Geshuai Luo

“…Experiments conducted on three load datasets from Australia, Panama and Austria show that UniLF achieves superior forecasting accuracy with competitive practical efficiency under different prediction lengths, providing a new solution for STLF.…”
Get full text

IM- LTS: An Integrated Model for Lung Tumor Segmentation using Neural Networks and IoMT by Jayapradha J, Su-Cheng Haw, Naveen Palanichamy, Kok-Why Ng, Senthil Kumar Thillaigovindhan

“…. • The results are measured based on the metrics such as, specificity, sensitivity, precision, accuracy and F-Score, using the data from benchmark datasets. Compared to the existing lung tumor segmentation and classification models, the proposed model provides better results and evidence for earlier disease diagnosis.…”
Get full text