Majority or Minority: Data Imbalance Learning Method for Named Entity Recognition by Sota Nemoto, Shunsuke Kitada, Hitoshi Iyatomi

“…., entity classes) and a single majority class (i.e., <inline-formula> <tex-math notation="LaTeX">$\mathcal {O}$ </tex-math></inline-formula>-class). …”
Get full text

Fully Vertical GaN-on-SiC p-i-n Diodes With BFOM of 2.89 GW/cm² by Jialun Li, Renqiang Zhu, Ka Ming Wong, Kei May Lau

“…The diode presents an ultra-low specific ON-resistance of 0.25 <inline-formula> <tex-math notation="LaTeX">$\text{m}\Omega \cdot $ </tex-math></inline-formula>cm2, a high current swing of 1011, and a high breakdown voltage of 850 V with a 5-<inline-formula> <tex-math notation="LaTeX">$\mu \text{m}$ </tex-math></inline-formula>-thick drift layer, leading to a Baliga&#x2019;s figure of merit (BFOM) of 2.89 GW/cm2. …”
Get full text

Federated Learning Based on Kernel Local Differential Privacy and Low Gradient Sampling by Yi Chen, Dan Chen, Niansheng Tang

“…Theoretical properties show that the proposed privacy-preserving mechanism has the properties of <inline-formula> <tex-math notation="LaTeX">$\epsilon $ </tex-math></inline-formula>-LDP and <inline-formula> <tex-math notation="LaTeX">$\epsilon $ </tex-math></inline-formula>-distance-LDP in the federated learning framework. …”
Get full text

Radiation Dose Calculations for a Hypothetical Accident in Xianning Nuclear Power Plant by Bo Cao, Junxiao Zheng, Yixue Chen

“…The results indicate that the maximum plume centerline ground deposition value of 1.2E+2 kBq/m2 occurred at about 1.4 km and the maximum TEDE value of 1.41E-05 Sv occurred at 1.4 km from the reactor. …”
Get full text

Effect of arm-ergometry versus treadmill supervised exercise on health-related quality of life and mental health in patients with peripheral artery disease: secondary outcomes from... by Sandra Magalhães, Mário Santos, Sofia Viamonte, Fernando Ribeiro, Joana Martins, Cristine Schmidt, Henrique Cyrne-Carvalho

“…Differences between groups in the change from baseline to the end of the study were analyzed using ANCOVA, adjusted for baseline values, or the Mann-Whitney U test. Results Fifty-six patients (66 ± 8.4 years; 87.5% male) were included: AEx (n = 28) and TEx (n = 28). …”
Get full text

A Review on Frequency Compensation and Transient Enhancement Schemes of Flipped Voltage Follower LDO Regulators for SoC Applications by P. Manikandan, B. Bindu

“…The transient performance of the FVF LDOs are measured based on the figure of merits and stability in terms of the phase margin. The proposed FVF LDO achieves a settling time of <inline-formula> <tex-math notation="LaTeX">$100 \ ns$ </tex-math></inline-formula> and PSR of <inline-formula> <tex-math notation="LaTeX">$-31\ dB\text{@}1\ MHz$ </tex-math></inline-formula>. …”
Get full text

Estimation of Forest Leaf Area Index Based on GEE Data Fusion Method by Xinyi Liu, Li He, Zhengwei He, Yun Wei

“…The study demonstrated that incorporating canopy heights into the estimation model led to an <inline-formula><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> model accuracy of greater than 0.83. …”
Get full text

A Joint Forgetting Factor-Based Adaptive Extended Kalman Filtering Approach to Predict the State-of-Charge and Model Parameter of Lithium-Ion Battery by Satyaprakash Rout, Satyajit Das

“…The accuracy of the SOC estimation is demonstrated by comparing the root mean square error (<inline-formula> <tex-math notation="LaTeX">$E_{RMS}$ </tex-math></inline-formula>) and maximum absolute error (<inline-formula> <tex-math notation="LaTeX">$Max_{AE}$ </tex-math></inline-formula>) with other Kalman filter-based estimators. …”
Get full text

Balancing Explainability and Privacy in Bank Failure Prediction: A Differentially Private Glass-Box Approach by Junyoung Byun, Jaewook Lee, Hyeongyeong Lee, Bumho Son

“…Our main findings are as follows: 1) In the absence of privacy constraints, the models consistently identified Asset Turnover, Total Debt / Invested Capital, and ROE ratios as the most influential factors in predicting bank failure, in that order; 2) When the privacy budget <inline-formula> <tex-math notation="LaTeX">$\epsilon \leq 1$ </tex-math></inline-formula>, only EBM maintained significant performance; 3) The reduction in explainability due to privacy protection was more pronounced for variables with initially lower explanatory power, while Asset Turnover retained its explanatory power even at <inline-formula> <tex-math notation="LaTeX">$\epsilon = 0.01$ </tex-math></inline-formula>. …”
Get full text

Optimized Resonators for Piezoelectric Power Conversion by Weston D. Braun, Eric A. Stolt, Lei Gu, Jeronimo Jeronimo Segovia-Fernandez, Sombuddha Chakraborty, Ruochen Lu, Juan M. Rivas-Davila

“…It achieves a maximum power output of 30.9&#x00A0;W at an efficiency of 95.2&#x0025; with a power density of 6.76&#x00A0;<inline-formula><tex-math notation="LaTeX">$\frac{\text {W}}{\text {cm}^3}$</tex-math></inline-formula>.…”
Get full text

Indoor Visible Light 3D Localization System Based on Black Wing Kite Algorithm by Jiahui Wang, Xiangqing Wang, Chaochuan Jia, Cui Yang

“…The simulation results show that in the indoor environment of 5m <inline-formula> <tex-math notation="LaTeX">$\times 5$ </tex-math></inline-formula>m <inline-formula> <tex-math notation="LaTeX">$\times 6$ </tex-math></inline-formula>m, the average error of 1.29cm and the maximum error of 6.29cm are achieved after 100 iterations and 90.02% of the average localization error is less than 2.39cm, the horizontal error is less than 2.20cm. …”
Get full text

Hybridize Machine Learning Methods and Optimization Techniques to Analyze and Repair Welding Defects via Digital Twin of Jidoka Simulator by Ahmed M. Abed, Tamer S. Gaafar

“…Hybridising the Random-Forest algorithm with Dingo optimisation and called Regulated Random Forest (RRF) to precisely identify defect clusters and then predict the welding defect growth rate (<inline-formula> <tex-math notation="LaTeX">$\boldsymbol {{R}_{s}}$ </tex-math></inline-formula>) using the Cat-boost optimiser, which is enhanced by a beetle search mechanism called CatBAS. …”
Get full text

Learning to Boost the Performance of Stable Nonlinear Systems by Luca Furieri, Clara Lucia Galimberti, Giancarlo Ferrari-Trecate

“…Our robustness result is tight, in the sense that all stabilizing policies are recovered as the <inline-formula><tex-math notation="LaTeX">$\mathcal {L}_{p}$</tex-math></inline-formula> -gain of the model mismatch operator is reduced to zero. …”
Get full text

Robust and Sparse Kernel-Free Quadratic Surface LSR via L_2,p-Norm With Feature Selection for Multi-Class Image Classification by Yongqi Zhu, Zhixia Yang, Junyou Ye, Yongxing Hu

“…In this study, a framework approach is introduced for the multi-classification problem based on the <inline-formula> <tex-math notation="LaTeX">$L_{2,p}$ </tex-math></inline-formula>-norm, utilizing more general loss functions and regularization terms, which is a robust sparse kernel-free quadratic surface least squares regression (RSQSLSR). …”
Get full text

Nonlinearity-Induced Spur Analysis in Fractional-<italic>N</italic> Synthesizers With &#x0394;&#x03A3; Quantization Cancellation by Yizhe Hu, Weichen Tao, Robert Bogdan Staszewski

“…While fractional-N phase-locked loops (PLLs) and injection-locking techniques with delta&#x2013;sigma <inline-formula> <tex-math notation="LaTeX">$(\Delta \Sigma )$ </tex-math></inline-formula> quantization cancellation using a digital-to-time converter (DTC) (and more recently, DACs) have demonstrated low-jitter performance and are well understood in terms of PN, their spur mechanisms still lack a comprehensive quantitative analysis. …”
Get full text

Subthreshold Kink Effect in Gate-All-Around MOSFETs Based on Void Embedded Silicon on Insulator Technology by Yuxin Liu, Qiang Liu, Jin Chen, Zhiqiang Mu, Xing Wei, Wenjie Yu

“…In this VESOI GAA device, a consistent and favorable decrease in subthreshold swing (SS) is observed as <inline-formula> <tex-math notation="LaTeX">$V_{\mathrm { d}}$ </tex-math></inline-formula> increases, which has rarely been reported in devices with other gate structures. …”
Get full text

Machine Learning-Based Normal White Blood Cell Multi-Classification Optimization by Taeyeon Gil, Sukjun Lee, Onseok Lee

“…Features used for WBC classification were determined through three experiments, resulting in a final selection of 108 features combining intensity histogram, hue saturation value, and CIE La<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula>b<inline-formula> <tex-math notation="LaTeX">$^{\ast }$ </tex-math></inline-formula> features. …”
Get full text

Design Optimization of a 3-PUU Parallel Machine for Friction Stir Welding Robots by Eka Marliana, Latifah Nurahmi, Arif Wahjudi, I. Made Londen Batan, Guowu Wei

“…Initially, a design space atlas was created, mapping both LCI and <inline-formula> <tex-math notation="LaTeX">$d_{1}$ </tex-math></inline-formula> were identified. …”
Get full text

Exploring Topic Coherence With PCC-LDA and BERT for Contextual Word Generation by Sandeep Kumar Rachamadugu, T. P. Pushphavathi, Surbhi Bhatia Khan, Mohammad Alojail

“…The above results of the topic-level analysis indicate that PCC-LDA consistency topics perform better than LDA and NMF(non-negative matrix factorization Technique) by at least 15.4%,12.9%(<inline-formula> <tex-math notation="LaTeX">$k = 5$ </tex-math></inline-formula>) and up to nearly 12.5% and 11.8% (<inline-formula> <tex-math notation="LaTeX">$k = 10$ </tex-math></inline-formula>) respectively, where k represents the number of topics.…”
Get full text

Robust Identification of Vegetation Change Using Shapelet-Based Temporal Segmentation of Landsat Time-Series Stacks: A Case Study in the Qilian Mountains by Lipeng Jiao, Randolph H. Wynne

“…Applied across the entire Qilian Mountains, it outperformed LandTrendr with 99.5&#x0025;<inline-formula><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula>0.4&#x0025; accuracy. …”
Get full text