Approximation-Aware Training for Efficient Neural Network Inference on MRAM Based CiM Architecture by Hemkant Nehete, Sandeep Soni, Tharun Kumar Reddy Bollu, Balasubramanian Raman, Brajesh Kumar Kaushik

“…Convolutional neural networks (CNNs), despite their broad applications, are constrained by high computational and memory requirements. …”
Get full text

Direct scribing of metal microgratings using sawtoothed cemented carbide tools with Johnson-Cook model-based plastic deformation simulation by Minwook Kim, Dae Bo Sim, Yong Tae Kim, Bo Hyun Kim, Jong G. Ok

“…Finite element analysis and friction-based modeling, incorporating the Johnson-Cook plasticity framework, capture the substrate deformation response and predict depth errors below 5 %, complementing the experimental results and validating parameter-based depth control. …”
Get full text

Cascade Nonlinear Observer-Based Speed-Sensorless Adaptive Twisting Sliding Mode Control of Linear Induction Motor by Lei Zhang, Xiaodong Xie, Dabiao Wu, Zicheng Wang, Jianli Wang, Jiaxin Jing, Huazhen Deng, Junkai Li, Jie Huang, Jingli Huang

“…The stability of the proposed cascade observer is analyzed using Lyapunov theory, ensuring the convergence of the estimation errors under bounded disturbances. Complementing the observer, two adaptive gain twisting sliding mode controllers are developed: one for speed tracking and another for flux regulation. …”
Get full text

Patch-Wise-Based Self-Supervised Learning for Anomaly Detection on Multivariate Time Series Data by Seungmin Oh, Le Hoang Anh, Dang Thanh Vu, Gwang Hyun Yu, Minsoo Hahn, Jinsul Kim

“…Multivariate time series anomaly detection is a crucial technology to prevent unexpected errors from causing critical impacts. Effective anomaly detection in such data requires accurately capturing temporal patterns and ensuring the availability of adequate data. …”
Get full text

GIS isolation switch contact temperature wireless monitoring by Liu Haoli, Li Jiaqi, Zhang Jiuye, Zhao Yubo, Zhang Jinhua, Wang Liang

“…It was found that the average absolute error of monitoring is 0.47%. This method can save economic costs and achieve the required accuracy for engineering applications.…”
Get full text

A novel method for assessing postmortem interval using radon radioisotopic decay – an internal radon ‘time of death clock’ by Behnam Ashrafkhani, Armin Tabesh, Fredrik Tamsen, Aaron A. Goodarzi, Martin Tondel, Robert Ian Thompson, Michael E. Wieser

“…A key innovation is the use of paired measurements taken at two postmortem time points to capture the time-derivative of the decay curve, enhancing solution uniqueness, reducing dependence on prior exposure history, therefore minimizing error. Monte Carlo simulations were employed to assess model performance. …”
Get full text

High-precision three-dimensional imaging based on binocular meta-lens and optical clue fusion by Yuzhou Song, Yifei Zhang, Xiaoyuan Liu, Takuo Tanaka, Mu Ku Chen, Zihan Geng

“…This hybrid approach achieves unprecedented precision of depth estimation (error <1%) while maintaining robust performance across feature-deficient surfaces. …”
Get full text

Accurate single-shot full-Stokes detection enabled by heterogeneous grain orientations in polycrystalline films by Mingwei Ge, Yuan Yao, Tyler Wang, Subhrangsu Mukherjee, Harald Ade, Mengxia Liu

“…Using deep learning, GOStokes precisely determines arbitrary polarization states with an averaged mean absolute error below 1%. Our demonstration underscores the potential of combining low-cost, scalable, polycrystalline films with reconstruction algorithms for advanced polarimetric applications.…”
Get full text

A Reconfigurable Digital Beamformer Implemented on a Field-Programmable Gate Array for Real-Time and Resource-Efficient Direction-of-Arrival Estimation by Yuting Wang, Liyuan Zhu, Tianxiang Wu, Shunli Ma

“…By dynamically switching operational modes and fine-tuning the granularity of processing tasks, this architecture maximizes the efficient use of Field-Programmable Gate Array (FPGA) resources, ensuring optimal performance and flexibility in real-time signal processing applications. Simulation results show that with an input signal-to-noise ratio of 10 dB, the beamformer can complete DOA estimation with an error of less than 1° within microsecond-level delay.…”
Get full text

Experimental and Numerical Study of Shape Memory Alloys for Vibration Amplitude Reduction in Mechanical Structures by Hyginus Chidiebere Onyekachi Unegbu, Danjuma Saleh Yawas, Bashar Dan-asabe, Abdulmumin Akoredeley Alabi

“…A finite element model was developed to simulate the behavior of the system, showing strong correlation with experimental data, with a root mean square error (RMSE) of less than 4%. The validated model was further used to predict SMA performance under conditions not tested experimentally, confirming its reliability for broader applications. …”
Get full text

Enhanced Moisture Retrieval Near Boundary Layer From Satellite Sounder Data Through Atmospheric‐Surface Radiance Separation by Ronglian Zhou, Di Di, Jun Li, Zhenglong Li

“…Validated against ERA5 and radiosonde observations, compared with the traditional Rt‐based method, the Ra‐based atmospheric profile retrievals show distinct improvements in boundary‐layer humidity retrieval with at least 20% error reduction. This approach provides a new thought to enhance humidity retrievals from hyperspectral sounders and benefits other quantitative applications such as data assimilation.…”
Get full text

Model based multi-loop predictive control scheme for multivariable processes by Arun Ramaveerapathiran, Muniraj Rathinam, Karuppiah Natarajan, Muthiah Athi, Patil Mounica

“…Simulation results show that the proposed method gives better response in terms of Integral Absolute Error value compared to multi-loop PI controller tuned by other methods. …”
Get full text

Generating context-specific sports training plans by combining generative adversarial networks. by Juquan Tan, Jingwen Chen

“…The model is evaluated quantitatively through metrics like mean square error (MSE) and generation time and qualitatively through subjective ratings from athletes and coaches using a five-point Likert scale for context-specific, scientificity, applicability, and feasibility. …”
Get full text

Concurrent validity of novel smartphone-based apps monitoring barbell velocity in powerlifting exercises. by Alexander Renner, Benedikt Mitter, Arnold Baca

“…The aim of this study was to determine the validity of three smartphone applications measuring barbell movement velocity in resistance training and comparing them to a commercially available linear transducer. …”
Get full text

Optimized deep neural network architectures for energy consumption and PV production forecasting by Eghbal Hosseini, Barzan Saeedpour, Mohsen Banaei, Razgar Ebrahimy

“…The results demonstrate that ODNN outperforms the average performance of other methods, achieving a 27% improvement in forecasting accuracy and a 22% reduction in error across various metrics. These findings demonstrate the significant potential of GA-PSO as an effective tool to optimize DNN models in energy forecasting applications.…”
Get full text

Design of an Optimal Convolutional Neural Network Architecture for MRI Brain Tumor Classification by Exploiting Particle Swarm Optimization by Sofia El Amoury, Youssef Smili, Youssef Fakhri

“…This performance-driven method avoids the inefficiencies of manual design and iterative trial and error. Experimental results indicate that the PSO-optimized CNN achieves a classification accuracy of 99.19%, demonstrating significant potential for improving diagnostic precision in complex medical imaging applications and underscoring the value of automated architecture search in advancing critical healthcare technology.…”
Get full text

Analysis of Reaction between α-Lipoic Acid and 2-Chloro-1-methylquinolinium Tetrafluoroborate Used as a Precolumn Derivatization Technique in Chromatographic Determination of α-Lip... by Magdalena Godlewska, Angelika Odachowska, Monika Turkowicz, Joanna Karpinska

“…The error of the determination did not exceed 0.5% in relation to the declared value.…”
Get full text

A Gradient-Based Optimization Algorithm for Optimal Control Problems With General Conformable Fractional Derivatives by Essia Ben Alaia, Slim Dhahri, Omar Naifar

“…Comprehensive comparisons including Caputo derivatives demonstrate 17.8% cost reduction and 40.1% lower terminal state error. Parameter sensitivity analyses further validate kernel selection strategies. …”
Get full text

Hole-Free Symmetric Complementary Sparse Array Design for High-Precision DOA Estimation by He Ma, Libao Liu, Zhihong Gan, Yang Gao, Xingpeng Mao

“…Simulation experiments in various scenarios have shown the advantages of the proposed array in DOA estimation, including a strong ability to estimate multi-targets, high angular resolution, low estimation error, and strong robustness to mutual coupling.…”
Get full text

An integrated approach to image quality: comparative analysis of bilinear and nearest neighbor interpolation by Wusat Ullah, Seher Ilyas, Hamza Naveed, Saalam Ali

“…To achieve a thorough evaluation of each interpolation method, we utilize a set of essential quality assessment metrics: Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Grayscale Analysis, and Mean Squared Error (MSE). These metrics were selected to provide a balanced assessment of image sharpness, structural accuracy, and overall visual quality. …”
Get full text