MalFormer: A Novel Vision Transformer Model for Robust Malware Analysis by In-Woong Jeong, Han-Ju Lee, Gwang-Nam Kim, Seok-Hwan Choi

“…Also, we introduce Sharpness-Aware Minimization (SAM) to optimize the training process of MalFormer. The proposed method enhances sensitivity to key features while maintaining a well-balanced integration of local and global features. …”
Get full text

A Machine Learning Approach to Volume Tracking in Multiphase Flow Simulations by Aaron Mak, Mehdi Raessi

“…It was trained using MATLAB’s (R2021a) Deep Learning Toolbox with a grid search method to find an optimal neural network configuration. …”
Get full text

Multifactor Stock Selection Strategy Based on Machine Learning: Evidence from China by Jieying Gao, Huan Guo, Xin Xu

“…The main findings are as follows: the support vector regression has the most stable successful rate for predicting, while ridge regression and linear regression have the most unstable successful rate with more extreme cases; algorithm of support vector regression fitting higher-degree polynomials in Chinese A-share market is optimized, compared with the traditional linear regression both in terms of stock return and retracement control; the results of support vector regression significantly outperforming the CSI 500 index prove further.…”
Get full text

A high performance approach to ensure image security during transmission by Adithya S Nair, Charvi Upreti, Advaith Arun, Renuka Devi S

“…By reducing runtime while maintaining data integrity and security, the method proves to be highly suitable for real-time applications. …”
Get full text

Configuring Transmission Thresholds in IIoT Alarm Scenarios for Energy-Efficient Event Reporting by David E. Ruiz-Guirola, Onel L. A. Lopez, Samuel Montejo-Sanchez

“…In low-density scenarios, all proposed methods outperform the benchmark, while in high-density scenarios, only Voronoi-(i), K-nearest neighbors, and Q-learning show better performance. …”
Get full text

A novel trajectory segmentation and compression approach for moving objects based on arc and polyline integration by Zhihong Ouyang, Lei Xue, Feng Ding, Mingxing Fang

“…Experimental results demonstrate that compared to typical polyline simplification methods, the proposed method further reduces the compression rate while maintaining good compressed trajectory accuracy.…”
Get full text

Learning-augmented sketching offers improved performance for privacy preserving and secure GWAS by Junyan Xu, Kaiyuan Zhu, Jieling Cai, Can Kockan, Natnatee Dokmai, Hyunghoon Cho, David P. Woodruff, S. Cenk Sahinalp

“…These SNPs are assigned dedicated memory to enable more precise selection of significant SNPs over the entire dataset while optimizing memory usage. Our method maintains the stringent privacy guarantees of SkSES, ensuring sensitive genotype data remains undisclosed to other institutions or cloud providers. …”
Get full text

Spectral Adaptive Dropout: Frequency-Based Regularization for Improved Generalization by Zhigao Huang, Musheng Chen, Shiyan Zheng

“…The proposed approach addresses the limitations of traditional dropout methods by adaptively targeting high-frequency components that typically contribute to overfitting while preserving essential low-frequency information. …”
Get full text

Interpretability Study of Gradient Information in Individual Travel Prediction by Ziheng Su, Pengfei Zhang, Xiaohui Song, Yifan Li

“…To address the shortcomings of existing XAI methods in analyzing the dynamic features of historical travel sequences, this paper introduces an alternative interpretability method based on gradient information, overcoming the interpretability bottleneck of travel prediction models. …”
Get full text

Sparse coding-based multiframe superresolution for efficient synchrotron radiation microspectroscopy by Yasuhiko Igarashi, Naoka Nagamura, Masahiro Sekine, Hirokazu Fukidome, Hideitsu Hino, Masato Okada

“…Additionally, our sparse coding method learns an optimal dictionary tailored for nanostructure extraction, fine-tuning the SR process to the unique characteristics of the data, even with noise and limited samples. …”
Get full text

Blocking Superantigen-Mediated Diseases: Challenges and Future Trends by Pengbo Wang, Zina Fredj, Hongyong Zhang, Guoguang Rong, Sumin Bian, Mohamad Sawan

“…Its mimicking peptide has been suggested as a potential candidate to block superantigens, but it can lead to reduced T-cell activity while increasing the host’s infection risk. Thus, this review focuses on the use of drug delivery methods to accurately target and block superantigens, while reducing the adverse effects associated with CD28 mimic peptides. …”
Get full text

A Hybrid Fuzzy Multicriteria Decision-Making Approach for Fighter Aircraft Selection: Application to the Algerian Air Force by Abdelghafour Kaanit, Kinza Nadia Mouss, Tarek Berghout

“…Results indicate that SU-34 is the optimal choice when using fuzzy AHP, while the F-16 ranks highest with the entropy method, with minimal score differences underscoring the precision and reliability of the methodology. …”
Get full text

Neuropsychological and clinical variables associated with cognitive trajectories in patients with Alzheimer's disease by Marianna Riello, Monica Moroni, Stefano Bovo, Flavio Ragni, Manuela Buganza, Raffaella Di Giacopo, Marco Chierici, Lorenzo Gios, Matteo Pardini, Matteo Pardini, Federico Massa, Federico Massa, Monica Dallabona, Elisa Vanzetta, Cristina Campi, Cristina Campi, Michele Piana, Michele Piana, Sara Garbarino, Manuela Marenco, Venet Osmani, Giuseppe Jurman, Antonio Uccelli, Antonio Uccelli, Bruno Giometto, Bruno Giometto, NeuroArtP3 Network, Filippo Gerli, Guido Pasquini, Claudia Niccolai, Matteo Betti, Emilio Portaccio, Maria Pia Amato, Rossi Andrea, Parodi Costanza, Ramaglia Antonia, Tortora Domenico, Severino Mariasavina, Andrea Falini, Antonella Castellano, Nicolò Pecco, Paola Scifo, Sonia Calloni

“…We used Mini Mental State Examination (MMSE) scores as outcome to identify the factors associated with cognitive decline at follow up.MethodsA sample of N = 126 patients diagnosed with AD (MMSE >19) were followed during 3 years in 4 time-points: T0 for the baseline and T1, T2 and T3 for the years of follow-ups. …”
Get full text

Clustering Library Loan Books Using K-Means Clustering by Mawar Indah Tanjung, Sriani Sriani

“…Without proper analysis, less popular books may remain in large quantities, while popular books may experience shortages. This study employs the K-Means Clustering method to group borrowed books at the Saintek UINSU Medan Library. …”
Get full text

Beyond the nuclear border: single-cell analysis of in situ sequenced human brain tissue using cellular features by Janssen M. Kotah, Thomas Rust, Hilmar R. J. van Weering, Janneke Bosma, Amber L. Woudstra, Susanne M. Kooistra, Bart J. L. Eggen

“…A key challenge in ISS data analysis is optimizing transcript allocation while minimizing misallocation, particularly in the morphologically complex central nervous system (CNS). …”
Get full text

Improved Combinatorial Benders Decomposition for a Scheduling Problem with Unrelated Parallel Machines by Francisco Regis Abreu Gomes, Geraldo Robson Mateus

“…For the second set the proposed method failed to find an optimal solution in only 31 in 600 instances, obtained an average gap of 0.07%, and took an average computational time of 377.86 s, while the best results of the other methods were 57, 0.17%, and 573.89 s, respectively.…”
Get full text

Using biometric data to protect information by K. N. Vlasov, O. V. Tolstykh, O. V. Isaev

“…An urgent task is to evaluate the system for protecting access to information while minimizing errors, based on the use of human biometric data. …”
Get full text

Dense Matching with Low Computational Complexity for Disparity Estimation in the Radargrammetric Approach of SAR Intensity Images by Hamid Jannati, Mohammad Javad Valadan Zoej, Ebrahim Ghaderpour, Paolo Mazzanti

“…Notably, unlike traditional local and global models, the computational complexity of the proposed approach remains stable as the input size or kernel dimensions increase while memory consumption stays low. Compared to a pyramid-based local normalized cross-correlation (NCC) algorithm and adaptive semi-global matching (SGM) models, the proposed method maintains good accuracy comparable to adaptive SGM while reducing processing time by up to 50% relative to pyramid SGM and achieving a 35-fold speedup over the local NCC algorithm with an optimal kernel size. …”
Get full text

Robot Trajectory Tracking Control Based on Neural Networks and Sliding Mode Control by Yuyun Liang

“…The traditional control method converged at 4.9s and the curve was relatively fluctuating, while the research method converged at 3.6s and the converged curve was relatively smooth and stable. …”
Get full text

Enhancing the nutritional profile of purple sweet potato flour through fermentation with Lactiplantibacillus plantarum InaCC B157: A functional food perspective by Tiurma Pasaribu, Yati Sudaryati Soeka, Novik Nurhidayat, Suciatmih Suciatmih, Titin Yulinery, Evi Triana, Tri Ratna Sulistiyani, Ninik Setyowati, Desty Dwi Sulistyowati, Dwi Ningsih Susilowati

“…Protein, fat, carbohydrates, fiber, and vitamins A and C also increased, while ash, anthocyanins, phenols, and steroids showed a decline. …”
Get full text