Digital Methods to Study (and Reduce) the Impact of Disinformation by Miriam Di Lisio, Domenico Trezza

“…Digital methods and text classification procedures are able to do this through predictive approaches to identify a suspect message or author. …”
Get full text

Oil Commodity Movement Estimation: Analysis with Gaussian Process and Data Science by Mulue Gebreslasie, Indranil SenGupta

“…In this study, Gaussian process (GP) regression is used to normalize observed commodity data and produce predictions at densely interpolated time intervals. …”
Get full text

Design of aperture radar auxiliary technology based on array mathematical model and statistical characteristic calculation by Ji Yang, Ying Fan, Shuqing Yang

Get full text

Exploration of potential biomarkers and immune cell infiltration characteristics for peripheral atherosclerosis in sjögren’s syndrome based on comprehensive bioinformatics analysis... by Chunjiang Liu, Yuan Wang, Lina Zhou, Feifei Cai, Xiaoqi Tang, Liying Wang, Xiang Zhang

“…Subsequently, machine learning algorithms and protein-protein interaction (PPI) network analysis were employed to further investigate potential predictive genes. …”
Get full text

Machine-learning models for differentiating benign and malignant breast masses: Integrating automated breast volume scanning intra-tumoral, peri-tumoral features, and clinical info... by Meixue Dai, Yueqiong Yan, Zhong Li, Jidong Xiao

“…Combining radiomics with clinical features further enhanced predictive performance. The LGBM model outperformed the other algorithms across subgroups, achieving a maximum AUC of 0.909, an accuracy of 0.878, and an F1-score of 0.971. …”
Get full text

Demographic bias mitigation at test-time using uncertainty estimation and human–machine partnership by Anoop Krishnan Upendran Nair, Ajita Rattani

“…Facial attribute classification algorithms frequently manifest demographic biases by obtaining differential performance across gender and racial groups. …”
Get full text

The analysis of strategic management decisions and corporate competitiveness based on artificial intelligence by Yang Pu, Hao Li, Wenjia Hou, Xingchen Pan

“…Finally, real-world data are applied to evaluate model performance across indicators such as training time, convergence speed, and prediction effectiveness. The results demonstrate that the hybrid model successfully converges within 150 iterations and exhibits substantial advantages over traditional algorithms, particularly in prediction accuracy for market share (92%), profit growth rate (91%), and customer satisfaction (89%). …”
Get full text

Brown bear optimized random forest model for short term solar power forecasting by Rathika Senthil Kumar, P.S. Meera, V. Lavanya, S. Hemamalini

“…Most of the ensemble ML algorithms outperform the traditional ML algorithms in terms of prediction accuracy. …”
Get full text

Combating electricity fraud: Employing hybrid learning and computer vision for sustainable energy management by Jui-Sheng Chou, Nader Anwar Charaf, Dani Nugraha Limantono, Hoang-Minh Nguyen

“…Additionally, the study explores hybrid and ensemble AI models that combine the best-performing algorithms to improve prediction accuracy. The performance of these models is rigorously evaluated using various performance metrics, with results showing that the machine learning model with hyperparameters optimized by a metaheuristic optimization algorithm achieved the highest prediction accuracy. …”
Get full text

Masked Feature Modeling for Generative Self-Supervised Representation Learning of High-Resolution Remote Sensing Images by Shiyan Pang, Hanchun Hu, Zhiqi Zuo, Jia Chen, Xiangyun Hu

“…This methodology has several advantages: 1) The hybrid CNN + Transformer architecture not only retains the advantages of the local feature representation of the CNN architecture but also has the full-text information modeling capabilities of the Transformer architecture; 2) the feature extraction network outputs multiscale features, and it is easier to add upsampling and a skip connection to improve the accuracy of the downstream dense prediction task; and 3) the pretrained MFM can be applied to various downstream tasks through fine-tuning with limited samples. …”
Get full text

Evaluating Leaf Water Potential of Maize Through Multi-Cultivar Dehydration Experiments and Segmentation Thresholding by Shuanghui Zhao, Yanqun Zhang, Pancen Feng, Xinlong Hu, Yan Mo, Hao Li, Jiusheng Li

“…In contrast, there was little difference in the predictive effectiveness of the models constructed for each cultivar and all three cultivars. …”
Get full text

Prognostic value of multi-PLD ASL radiomics in acute ischemic stroke by Zhenyu Wang, Yuan Shen, Xianxian Zhang, Qingqing Li, Congsong Dong, Shu Wang, Haihua Sun, Mingzhu Chen, Xiaolu Xu, Pinglei Pan, Pinglei Pan, Zhenyu Dai, Fei Chen, Fei Chen

“…IntroductionEarly prognosis prediction of acute ischemic stroke (AIS) can support clinicians in choosing personalized treatment plans. …”
Get full text

Investigation of aromatic compounds and olfactory profiles in cocoa pulp fermentation using yeast-based starters: A Volatilomics and machine learning approach by Haode Chang, Chunhe Gu, Quanmiao Zhang, Wenjing Zhang, Liru Ma, Fei Liu, Zhen Feng

“…The models showed high prediction accuracy, ranging from 0.85 for sourness by Gradient Boost Machine to 0.28 for sweetness by linear regression. …”
Get full text

Efficient Trans-Dimensional Bayesian Inversion of C-Response Data from Geomagnetic Observatory and Satellite Magnetic Data by Rongwen Guo, Shengqi Tian, Jianxin Liu, Yi-an Cui, Chuanghua Cao

Get full text

Research and prospect of reversible data hiding method with contrast enhancement by Yang YANG, Wei-ming ZHANG, ong-dong HOUD, Hui WANG, Neng-hai YU

“…Reversible data hiding methods can recover the cover image losslessly after extracting the secret message from the marked image.Such technology can be used in the certification or the label of military,justice and medical images,which are sensitive and slight modification are not allowed.Especially for the medical images,RDH tech-nology can be used in protecting the privacy of the patient.A series of RDH methods with contrast enhancement ef-fect were introduced and classified into pixel-based histogram methods and prediction-error-based histogram meth-ods according to the type of carrier in RDH scheme.The main purpose of such algorithms was to improve the sub-jective visual quality of marked images and to embed secret data into cover image reversibly meanwhile.These se-ries of algorithms were suitable for the research of privacy protection of medical image.Finally,future development in this direction is prospected through analyzing the advantages and disadvantages of the existing work.…”
Get full text

Delay-Driven Routing for Low-Duty-Cycle Sensor Networks by Zuzhi Fan

“…We compare our design against state-of-the-art routing algorithms derived in wireless networks through large-scale simulations and testbed experiments, which show that our algorithms can achieve a significant reduction in delivery delay.…”
Get full text

Explainable Feature Engineering for Multi-class Money Laundering Classification by Petre-Cornel GRIGORESCU, Antoaneta AMZA

“…This paper provides insight into typical money laundering typologies used in the financial crime domain and provides a concrete set of methods through the use of which fraudulent transactions may be classified using traditional machine learning algorithms and proving the efficacy of tree-based models in not only predictive power, but also explainability and ease of interpretation of results.…”
Get full text

Decentralized multi-agent federated and reinforcement learning for smart water management and disaster response by H. Mancy, Naglaa E. Ghannam, Amr Abozeid, Ahmed I. Taloba

“…Experimental results validate that it has lower MSE, higher R² scores, and quicker response times, making it better suited for flood prediction and disaster response. To this end, this study advances a solution through a Decentralized Learning-Driven Multi-Agent Autonomous System (DL-MAAS). …”
Get full text

SECTOR LOCALIZATION, PARAMETERIZATION AND IDENTIFICATION OF REFERENCE POINTS BASED ON CORNER COEFFICIENTS FOR ALIGNING THE OVERLAPPING IMAGES by O. J. Al-Furaiji, V. K. Kanapelka, V. YU. Tsviatkou

“…It is shown that these algorithms compared to the methods of SIFT and SURF provide a reduction in the computational complexity of localization and parameterization of reference points and increase the stability of their descriptors at parallax.…”
Get full text

Relationship between intra-bladder pressure and acute kidney injury in patients with acute pancreatitis: interpretable machine learning approach by Gang Liao, Baning Ye, Jianquan Li, Mingxiang Wen

“…Then, the ML algorithm is used to establish the prediction model. …”
Get full text