Learning-based early detection of post-hepatectomy liver failure using temporal perioperative data: a nationwide multicenter retrospective study in ChinaResearch in context by Kai Wang, Qian Yang, Kang Li, Shanhua Tang, Baoluhe Zhang, Xiangyun Liao, Shunda Du, Wenguang Fu, Zhiwei Li, Huanwei Chen, Haorong Xie, Pengxiang Huang, Jieyuan Li, Qiuting Wang, Haiqing Liu, Zhiwei Huang, Pheng Ann Heng, Xueshuai Wan, Chuanjiang Li, Weixin Si

“…The proposed algorithm employed a powerful foundation model (Bio-Clinical Bidirectional Encoder Representation from Transformers) and a context-aware transformer module to perform in-depth temporal feature investigation of perioperative data to enable early detection of PHLF. …”
Get full text

Multimodal multilevel attention for semi-supervised skeleton-based gesture recognition by Jinting Liu, Minggang Gan, Yuxuan He, Jia Guo, Kang Hu

“…To resolve this problem, we propose a novel multimodal multilevel attention network designed for semi-supervised learning. This model utilizes the self-attention mechanism to polymerize multimodal and multilevel complementary semantic information of the hand skeleton, designing a multimodal multilevel contrastive loss to measure feature similarity. …”
Get full text

Prognostic Implications of the Number of Lymph Node Metastases in Oral Tongue Squamous Cell Carcinoma: A Population Study of the SEER Database and an Institutional Registry by Wenjie Huang, Yu Zhang, Hao Li, Zhiying Liang, Shumin Zhou, Jie Pan, Hui Xie, Chao Luo, Shuqi Li, Guangying Ruan, Fei Ai, Yanfeng Chen

“…External validation was performed via the SEER registry. Multivariate Cox proportional hazards model was employed to calculate hazard ratios (HRs) and 95% confidence intervals (CIs) of pathological nodal features. …”
Get full text

A Rice-Mapping Method with Integrated Automatic Generation of Training Samples and Random Forest Classification Using Google Earth Engine by Yuqing Fan, Debao Yuan, Liuya Zhang, Maochen Zhao, Renxu Yang

“…Finally, a random forest (RF) probabilistic model trained by integrating data from different phenological periods was used for rice mapping. …”
Get full text

MSNet: A multispectral-image driven rapeseed canopy instance segmentation network by Yuang Yang, Xiaole Wang, Fugui Zhang, Zhenchao Wu, Yu Wang, Yujie Liu, Xuan Lv, Bowen Luo, Liqing Chen, Yang Yang

“…In addition, comparisons with various RGB-only instance segmentation models show that all the proposed MSNet-HAFB fusion models significantly outperform single-modal models in rapeseed count detection tasks, confirming the potential advantages of multispectral fusion strategies in agricultural target recognition. …”
Get full text

A Frequency-Aware Transformer for Multiscale Fault Diagnosis in Electrical Machines by Yurim Choi, Inwhee Joe

“…FAMFT overcomes the limitations of conventional CNN- and RNN-based models through three key innovations: 1) Multi-scale feature extraction via parallel analysis of fine-, intermediate-, and long-term temporal scales, 2) Selective feature enhancement through a frequency gating mechanism, and 3) An interpretable fault diagnosis framework based on SHAP (SHapley Additive Explanations). …”
Get full text

IoT intrusion detection method for unbalanced samples by ANTONG P, Wen CHEN, Lifa WU

“…In recent years, network traffic increases exponentially with the iteration of devices, while more and more attacks are launched against various applications.It is significant to identify and classify attacks at the traffic level.At the same time, with the explosion of Internet of Things (IoT) devices in recent years, attacks on IoT devices are also increasing, causing more and more damages.IoT intrusion detection is able to distinguish attack traffic from such a large volume of traffic, secure IoT devices at the traffic level, and stop the attack activity.In view of low detection accuracy of various attacks and sample imbalance at present, a random forest based intrusion detection method (Resample-RF) was proposed, which consisted of three specific methods: optimal sample selection algorithm, feature merging algorithm based on information entropy, and multi-classification greedy transformation algorithm.Aiming at the problem of unbalanced samples in the IoT environment, an optimal sample selection algorithm was proposed to increase the weight of small samples.Aiming at the low efficiency problem of random forest feature splitting, a feature merging method based on information entropy was proposed to improve the running efficiency.Aiming at the low accuracy problem of random forest multi-classification, a multi-classification greedy transformation method was proposed to further improve the accuracy.The method was evaluated on two public datasets.F1 reaches 0.99 on IoT-23 dataset and 1.0 on Kaggle dataset, both of which have good performance.The experimental results show that the proposed model can effectively identify the attack traffic from the massive traffic, better prevent the attack of hackers on the application, protect the IoT devices, and thus protect the related users.…”
Get full text

HybridFormer: a convolutional neural network-Transformer architecture for low dose computed tomography image denoising by Shanaz Sharmin Jui, Zhitao Guo, Rending Jiang, Jiale Liu, Bohua Li

“…Firstly, this algorithm constructs residual convolution for local feature extraction and Swin Transformer for global feature extraction, boosting denoising efficacy. …”
Get full text

Accelerated and accurate cervical cancer diagnosis using a novel stacking ensemble method with explainable AI by Md Ismail Hossain Siddiqui, Shakil Khan, Zishad Hossain Limon, Hamdadur Rahman, Mahbub Alam Khan, Abdullah Al Sakib, S M Masfequier Rahman Swapno, Rezaul Haque, Ahmed Wasif Reza, Abhishek Appaji

“…Techniques like contrast enhancement and data augmentation were employed to optimize feature extraction. The model achieved state-of-the-art performance, attaining an accuracy of 99.38 % and an F1-score of 98.49 % on the Herlev dataset and an accuracy of 98.71 % and an F1-score of 97.53 % on SIPaKMeD. …”
Get full text

Impact of splenectomy on prognosis in lymphoma with splenic involvement by Li Li, Mengqi Xiong, Lulu Wang, Lixia Zhu, Kui Zhao, Lijun Wang, Jingsong He, Xiujin Ye

“…The collected data encompassed clinical presentations, diagnostic methods, histopathological features, treatment regimens, and outcomes. Kaplan–Meier survival analysis was performed to generate survival curves for overall survival (OS) and progression-free survival (PFS), with statistical significance assessed using the log-rank test. …”
Get full text

Congenital Epidermolysis Bullosa Epidemiology among Children of Russian Federation by Nikolay N. Murashkin, Roman V. Epishev, Olga S. Orlova, Alena А. Kuratova, Victoriya S. Polenova

“…Methods. We have performed analysis of the clinical and epidemiological features among pediatric population of Russian Federation with СEB using the “Registers of Genetic and Other Rare Diseases” of the “Butterfly Children” charitable foundation. …”
Get full text

Assessing Gonipterus defoliation levels using multispectral unmanned aerial vehicle (UAV) data in Eucalyptus plantations by Phumlani Nzuza, Michelle L. Schröder, Rene J. Heim, Louis Daniels, Bernard Slippers, Brett P. Hurley, IIaria Germishuizen, Benice Sivparsad, Jolanda Roux, Wouter. H Maes

“…XGBoost, Support Vector Machine and Random Forest (RF) were used to predict damage levels using five input spectral data types. XGBoost performed best, closely followed by RF. Both models consistently selected very similar features. …”
Get full text

Explainable olive grove and grapevine pest forecasting through machine learning-based classification and regression by F. Rodríguez-Díaz, A.M. Chacón-Maldonado, A.R. Troncoso-García, G. Asencio-Cortés

“…The results showed high precision in predicting pest outbreaks, particularly for the olive fly, with minimal differences between models using feature selection. In the vineyard dataset, the selection of characteristics improved the performance of the model by reducing the MAE and increasing R2. …”
Get full text

Multifeatures Fusion and Nonlinear Dimension Reduction for Intelligent Bearing Condition Monitoring by Liang Guo, Hongli Gao, Haifeng Huang, Xiang He, ShiChao Li

“…Meanwhile some comparative studies are performed; the results show the advantage of the proposed method in adaptive features selection and superior accuracy in bearing condition recognition.…”
Get full text

Machine learning helps reveal key factors affecting tire wear particulate matter emissions by Zhenyu Jia, Jiawei Yin, Tiange Fang, Zhiwen Jiang, Chongzhi Zhong, Zeping Cao, Lin Wu, Ning Wei, Zhengyu Men, Lei Yang, Qijun Zhang, Hongjun Mao

“…Model explainability results show that the feature parameters-emission response relationships for tire wear PM2.5 and PM2.5-10 are different. …”
Get full text

A Gamified Assessment Tool for Antisocial Personality Traits (Antisocial Personality Traits Evidence-Centered Design Gamified): Randomized Controlled Trial by Yaobin Tang, Yongze Xu, Qunli Zhou, Ran Bian

“…Empirical validation (study 3): a 2×2 mixed design (n=148) was used to compare the gamified assessment with questionnaires under conditions involving incentives (ie, situations in which “rational results” led to increased payments). ResultsFor model performance, the gated recurrent unit outperformed the alternatives, as indicated by the highest criterion correlation (r=0.850) and the lowest test RMSE (0.273); in particular, it excelled in moderate score ranges (1.5-3, RMSE≤0.377) and in resisting extreme value distortions (3.5-4, RMSE 0.854). …”
Get full text

Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments by Luc Builtjes, Sascha Caron, Polina Moskvitina, Clara Nellist, Roberto Ruiz de Austri, Rob Verheyen, Zhongyi Zhang

“…Our results in event classification show that the integration of all physics-motivated features improves background rejection by $10\%-40\%$ over baseline models, with an additional gain of up to $9\%$ due to the SM interaction matrix. …”
Get full text

The role of product art design based on a fuzzy decision support system in improving user interaction experience. by Yuqiao Liu, Shuai Zhang

“…This article introduces an interaction-based fuzzy decision support (FDS) system to meet user demands in product design through suggestions for user interaction. The proposed system models the maximum possible interaction features through previous user experiences and reviews. …”
Get full text

Prediction of all-cause mortality in Parkinson’s disease with explainable artificial intelligence using administrative healthcare data by You Hyun Park, Yong Wook Kim, Dae Ryong Kang, Sang Chul Lee, Seo Yeon Yoon

“…The most important contributing feature to PD mortality was age, followed by male sex and pneumonia. …”
Get full text

Enhancing MANET Security Through Long Short-Term Memory-Based Trust Prediction in Location-Aided Routing Protocols by Saad Mohsen Hassan, Mohd Murtadha Mohamad, Farkhana Binti Muchtar

“…LSTMT-LAR utilizes a 13-feature behavioral model to assess node trustworthiness in real-time, enabling proactive detection of malicious nodes. …”
Get full text