A robust, deep learning-based analysis of time-domain signals for NMR spectroscopy by Kyungdoe Han, Eunhee Kim, Kyoung-Seok Ryu, Donghan Lee

“…As a proof of concept, we present the resulting spectra, along with peak lists predicted by supplying only FID input to the deep learning algorithm. The generated peak lists can be considered as spectra with infinite resolution.…”
Get full text

TIBW: Task-Independent Backdoor Watermarking with Fine-Tuning Resilience for Pre-Trained Language Models by Weichuan Mo, Kongyang Chen, Yatie Xiao

“…By implementing a Trigger–Target Word Pair Search Algorithm that selects trigger–target word pairs with maximal semantic dissimilarity, our approach ensures that the watermark remains effective even after extensive fine-tuning. …”
Get full text

Research on Integrated Control Strategy for Highway Merging Bottlenecks Based on Collaborative Multi-Agent Reinforcement Learning by Juan Du, Anshuang Yu, Hao Zhou, Qianli Jiang, Xueying Bai

“…An integrated control system based on the Factored Multi-Agent Centralized Policy Gradients (FACMAC) algorithm is developed. By transforming the control framework into a Decentralized Partially Observable Markov Decision Process (Dec-POMDP), state and action spaces for heterogeneous agents are designed. …”
Get full text

Traffic Risk Assessment Based on Warning Data by Tao Wang, Binbin Chen, Yuzhi Chen, Shejun Deng, Jun Chen

“…The risk classification thresholds were determined based on the Gaussian Mixture Model algorithm. Finally, a spatial econometric model was used to quantify the impact of built environment factors characterized by Point of Interest (POI) data on regional traffic risk, with the results of risk class classification as the dependent variable. …”
Get full text

Measurement of snowpack density, grain size, and black carbon concentration using time-domain diffuse optics by Connor Andrew Henley, Colin Richard Meyer, Jacob Ian Chalif, Joseph Lee Hollmann, Ramesh Raskar

“…We introduce a model that predicts the time-dependent reflectance of a dry snowpack as a function of its density, grain size, and black carbon content. We develop an algorithm that retrieves these properties from measurements at two wavelengths. …”
Get full text

Flow Shift from Urban Roads to Beltway Expressway under a Tradable Credit Scheme to Alleviate Urban Traffic Congestion by Jimeng Tang, Yongxiang Zhu, Yue Yu, Lu Cai

“…Within this framework, a gradient projection method is utilized within the augmented Lagrangian multiplier algorithm to solve the lower-level problem and evaluate the fitness of the TCS. …”
Get full text

An Automatic Extraction Method of Coach Operation Information from Historical Trajectory Data by Jun Li, Qingqi Li, Yan Zhu, Yan Ma, Yubin Xu, Chao Xie

“…The method first analyzes trajectory characteristics of coaches within stations and identifies the highly dense point clusters as coach stations using the DBSCAN clustering algorithm. Then the schedule information is obtained by conducting error adjustment on the actual arrival and departure time series of multiple shifts, and the name of coach station is queried from point of interest (POI) and geographical name database provided by online map. …”
Get full text

MUFFNet: lightweight dynamic underwater image enhancement network based on multi-scale frequency by Dechuan Kong, Dechuan Kong, Yandi Zhang, Xiaohu Zhao, Yanqiang Wang, Lei Cai

“…A Multi-Scale Enhancement Prior algorithm enhances high-frequency and low-frequency features while the Information Flow Interaction module mitigates information stratification and blockage. …”
Get full text

Mape: defending against transferable adversarial attacks using multi-source adversarial perturbations elimination by Xinlei Liu, Jichao Xie, Tao Hu, Peng Yi, Yuxiang Hu, Shumin Huo, Zhen Zhang

“…MAPE comprises the single-source adversarial perturbation elimination (SAPE) mechanism and the pre-trained models probabilistic scheduling algorithm (PPSA). SAPE utilizes a thoughtfully designed channel-attention U-Net as the defense model and employs adversarial examples generated by a pre-trained model (e.g., ResNet) for its training, thereby enabling the elimination of known adversarial perturbations. …”
Get full text

Multiobjective Optimization of Hard Turning on OHNS Steel Using Desirability and TOPSIS Approaches by C. Manikandan, B. Rajeswari, Dhanesh G. Mohan, R. M. Aravind

“…RSM solution with 81.3% desirability, the cutting speed of 60 m/min, feed rate of 0.08 mm/rev, and depth of cut 1 mm as the optimal cutting parameters; similarly, TOPSIS algorithm calculation identifies the cutting parameter combinations, such as 40 m/min cutting speed, 0.09 mm/rev feed rate, and 1 mm depth cut to enrich the quality of the machined steel; however, the desirability approach cutting parameter setting is better for the surface finish achievement, while TOPSIS solution is better to obtain significant MRR. …”
Get full text

Model for sustainable carbon emission reduction energy development and smart grid technology strategy by Kangli Xiang, Keren Chen, Simin Chen, Wanqing Chen, Jinyu Chen

“…The model used the carbon trading mechanism to further reduce carbon emissions and the carnivorous plant algorithm to optimize the scheduling strategy. The results indicate that the model demonstrates significant advantages in terms of carbon emission, total operating cost, prediction accuracy, and energy utilization efficiency, respectively, at 60.8 kg, 2517.5 yuan, 96.5%, and 90.2%, indicating that it utilizes energy more fully and helps to enhance the overall energy efficiency of the system. …”
Get full text

Privacy-preserving incentive mechanism for integrated demand response: A homomorphic encryption-based approach by Wen-Ting Lin, Guo Chen, Jueyou Li, Yan Lei, Wanli Zhang, Degang Yang, Tingzhen Ming

“…To further protect privacy and encourage participation, a fully distributed algorithm incorporating homomorphic encryption is employed. …”
Get full text

The Small-Signal Stability of Offshore Wind Power Transmission Inspired by Particle Swarm Optimization by Jiening Li, Hanqi Huang, Xiaoning Chen, Lingxi Peng, Liang Wang, Ping Luo

“…In order to improve the weak damping of the power system, this paper presents a method to determine the parameters of the power system stabilizer (PSS) based on the particle swarm optimization (PSO) algorithm combined with different inertia weight functions. …”
Get full text

Analysis of ACAM Data for Trace Gas Retrievals during the 2011 DISCOVER-AQ Campaign by C. Liu, X. Liu, M. G. Kowalewski, S. J. Janz, G. González Abad, K. E. Pickering, K. Chance, L. N. Lamsal

“…Correcting ACAM radiance in direct-fitting based ozone profile algorithm significantly improves the consistency with OMI total ozone.…”
Get full text

Voltage-driven autonomous cooperative control of EHLs for load stabilization by Bing Qi, Rui Liu, Deying Zhang, Zhuoqun Wang, Qi Qi

“…Finally, a Q-decomposition Multi-agent Independent eXtension (QMIX) algorithm is used to learn the mapping relation, and the EHLs real-time optimal control strategies are generated through the utilization of Centralized Training Decentralized Execution (CTDE) framework. …”
Get full text

A Granulocyte-Specific Protein S100A12 as a Potential Prognostic Factor Affecting Aggressiveness of Therapy in Patients with Juvenile Idiopathic Arthritis by Krzysztof Orczyk, Elzbieta Smolewska

“…Further elaboration on the clinical algorithm is necessary for that protein to be included in everyday practice.…”
Get full text

Structural reliability analysis of steel structural covering based on the theory of evidence by S. A. Solov’ev, A. E. In’kov, A. A. Solov’eva, V. A. Smirnov

“…The graphical interpretation of the reliability analysis algorithm is given. It allows to obtain clearly and operatively an estimate of the failure probability of the structural element, as well as to reduce the permissible load on the element to the required reliability level. …”
Get full text

A Virtual Synchronous Generator Control Strategy Based on Transient Damping Compensation and Virtual Inertia Adaptation by Yan Xia, Yang Chen, Yao Wang, Renzhao Chen, Ke Li, Jinhui Shi, Yiqiang Yang

“…In addition, based on the TDC algorithm, an improved virtual inertia adaptive strategy utilizing the Inverse Square Root Unit (ISRU) approach is designed, and the tuning range of parameters is provided. …”
Get full text

Comparison and Estimation of Surface Albedo of Various Levels of Land use by SEBAL and METRIC Methods by Mehdi Asadi, Khalil Valizadeh khamran, Mohammad Baaghdeh, Hamed Adab

“…To determine the type of usage of different levels, the maximum likelihood algorithm classification method was used with Kappa coefficient of 86.14% and overall accuracy of 92.63%. …”
Get full text

Computer-Assisted Quantitative Analysis of Skeletal Muscles of Snowboarding Parallel Giant Slalom Athletes after Exercise Based on Artificial Intelligence and Complex Networks by Haiqiang Yu, Fei Yang, Jin Wang

“…In addition, a motion target positioning algorithm was used to obtain some motion parameters, which provided direct help for athletes in rationally arranging training load and scientific training. …”
Get full text