Enhancing Credit Risk Decision-Making in Supply Chain Finance With Interpretable Machine Learning Model by Guanglan Zhou, Shiru Wang

“…This study clarified the applicability and limitations of various models, highlighting the superior performance and interpretability of XGBoost through the SHAP algorithm. Ultimately, the insights from this study provided valuable guidance for companies and financial institutions, fostering more sustainable allocation of financial resources.…”
Get full text

Solar Field Mapping and Dynamo Behavior by Kenneth H. Schatten

“…The domain of this algorithmic model is the Sun’s photosphere. Within this computational space are placed two types of entities or agents; one may refer to them as bluebirds and cardinals; the former carries outward magnetic flux and the latter carries out inward magnetic flux. …”
Get full text

Multi-dimensional adaptive transmission technique for shortto-medium reach optical fiber communication system by Ming TANG, Xi CHEN

“…According to the features of short-to-medium reach optical fiber communication systems,three high performance adaptive modulation and coding schemes were investigated.In the first one,a new dimension,forward error correction (FEC),was introduced to the traditional bit and power loading (BPL) scheme,and the three-dimensional adaptive modulation and coding were achieved.The modulation format and FEC code were allocated based on look-up table (LUT).The proposed algorithm has lower complexity and higher data rate compared to the BPL scheme.The second one was also based on LUT method where one similar data rate with the BPL scheme was achieved using partitioned precoding,but peak-to-average power ratio was reduced up to two dB,and the power efficiency was improved.In the last scheme,probabilistic shaping QAM was adopted as the modulation format,and shaping gain and almost indefinitely fine modulation granularity were achieved at the expense of certain complexity.With adaptive partitioned precoding,without decreasing data rate the number of PS-QAM was limited to reduce the complexity.The experimental results demonstrate that the proposed scheme outperforms the BPL scheme in terms of data rate and receiver sensitivity.…”
Get full text

Constructing the Fuzzy Hyperbola and Its Applications in Analytical Fuzzy Plane Geometry by Seçil Özekinci, Cansel Aycan

“…We show the use of the algorithm for calculating the coefficients in the conic equation on the examples. …”
Get full text

Hierarchical Learning: A Hybrid of Federated Learning and Personalization Fine-Tuning by Li Shuyi, Zhang Bairong

“…This study proposes a hierarchical model that mitigates these challenges by incorporating a global model, trained using the Federated Averaging (FedAvg) algorithm, and applying client-specific fine-tuning to improve local model performance. …”
Get full text

Effect of International Technology Transfer on the Technical Efficiency of High-Tech Manufacturing in China: A RAGA-PP-SFA Analysis by Shuzhen Zhou, Qunzhao Deng, Feng Peng

“…By integrating stochastic frontier analysis (SFA) and projection pursuit (PP) based on the real-coded accelerated genetic algorithm (RAGA), this study constructed a RAGA-PP-SFA model that considers undesirable outputs. …”
Get full text

Inverse Kinematics Optimization Method of a 6-DOF Robot by Jian Wang, Yu Ao

“…Aiming at the problem of difficulty and uncertainty of object attitude recognition， a 6-axis robot attitude solution algorithm based on object position information is proposed. …”
Get full text

Fault Identification of Rolling Bearing Using Variational Mode Decomposition Multiscale Permutation Entropy and Adaptive GG Clustering by Tianjing He, Rongzhen Zhao, Yaochun Wu, Chao Yang

“…Finally, low-dimensional sensitive features obtained by principal component analysis (PCA) are fed into the adaptive GG clustering algorithm to perform fault identification. In this method, the residual energy ratio is used to find the optimal parameter K of the VMD and the PBMFfunction is incorporated into the GG to determine the number of clusters adaptively. …”
Get full text

Fast Spectral Clustering via Efficient Multilayer Anchor Graph by Yiwei Wei, Chao Niu, Dejun Liu, Peinan Ren

“…Against this backdrop, a novel algorithm named fast spectral clustering via efficient multilayer anchor graph (FEMAG) is proposed to resolve the accuracy and time-consuming trade-off problem. …”
Get full text

Autonomous Robotic Manipulation: Real-Time, Deep-Learning Approach for Grasping of Unknown Objects by Malak H. Sayour, Sharbel E. Kozhaya, Samer S. Saab

“…Our approach aims at reducing propagation errors and eliminating the need for complex hand tracking algorithm, image segmentation, or 3D reconstruction. …”
Get full text

Identification of the Hub Genes Involved in Stem Cell Treatment for Intervertebral Disc Degeneration: A Conjoint Analysis of Single-Cell and Machine Learning by Jianfeng Chen, Fuwei Qi, Guanshen Li, Qiaosong Deng, Chenlin Zhang, Xiaojun Li, Yafeng Zhang

“…The critical genes identified by the machine learning algorithm could provide new perspectives on IDD.…”
Get full text

Automatic Image Colorization Based on Convolutional Neural Networks by L. V. Serebryanaya, V. V. Potaraev

“…Experiments shown that developed model determines image color quite correctly. Proposed algorithm allows to use convolutional neural network for colorizing black-and-white images, for color correction of pictures, etc.…”
Get full text

A hybrid model for smart grid theft detection based on deep learning by Yinling LIAO, Jincan LI, Bing WANG, Jun ZHANG, Yaoyuan LIANG

“…A hybrid deep learning model was proposed to effectively detect electricity theft in smart grids.The hybrid model employed a deep learning convolutional neural network (AlexNet) to tackle the curse of dimensionality, significantly enhancing data processing accuracy and efficiency.It further improved classification accuracy by differentiating between normal and abnormal electricity usage using adaptive boosting (AdaBoost).To resolve the issue of class imbalance, undersampling techniques were utilized, ensuring balanced performance across various data classes.Additionally, the artificial bee colony algorithm was used to optimize hyperparameters for both AdaBoost and AlexNet, effectively boosting overall model performance.The effectiveness of this hybrid model was evaluated using real smart meter datasets from an electricity company.Compared to similar models, this hybrid model achieves accuracy, precision, recall, F1-score, Matthews correlation coefficient (MCC), and area under the curve-receiver operating characteristic curve (AUC-ROC) scores of 88%, 86%, 84%, 85%, 78%, and 91%, respectively.The proposed model not only increases the accuracy of electricity usage monitoring, but also offers a new perspective for intelligent analysis in power systems.…”
Get full text

Abnormal Event Detection in Wireless Sensor Networks Based on Multiattribute Correlation by Mengdi Wang, Anrong Xue, Huanhuan Xia

“…Experimental results show that the proposed algorithm can reduce the impact of interference factors and the rate of the false alarm effectively; it can also improve the accuracy of event detection.…”
Get full text

Inversion Calculation Analysis of Operational Tunnel Structure Based on the Distributed Optical-Fiber Sensing System by Jie Zhao, Jiang Feng, Liang Ren

“…In the end, this paper carries out parameter identification based on the differential evolution algorithm. Achievements of the study proved that real-time safety warning could be realized inside the tunnel by monitoring the deformation parameters of tunnel vault at real time relying on the optical-fiber sensing system of the optical time domain reflectometer (OTDR). …”
Get full text

High-Speed Target Identification System Based on the Plume’s Spectral Distribution by Wenjie Lang, Guoguang Chen, Xiaoli Tian, Changfan Xin

“…The distinguishing factor recognition algorithm was designed on basis of ratio of multifeature band peaks and valley mean values. …”
Get full text

Deep reinforcement learning based task allocation mechanism for intelligent inspection in energy Internet by Siya XU, Yifei XING, Shaoyong GUO, Chao YANG, Xuesong QIU, Luoming MENG

“…In order to reduce the cost and improve efficiency of power line inspection, UAV (unmanned aerial vehicle), which use mobile edge computing technology to access and process service data, are used to inspect power lines in the energy internet.However, due to the dynamic changes of UAV data transmission demand and geographical location, the edge server load will be unbalanced, which causes higher service processing delay and network energy consumption.Thus, an intelligent inspection task allocation mechanism for energy internet based on deep reinforcement learning was proposed.First, a two-layer edge network task offloading model was established to archive joint optimization of multi-objectives, such as delay and energy consumption.It was designed by comprehensively considering the route of UAV and edge nodes, different demands of services and limited service capabilities of edge nodes.Furthermore, based on Lyapunov optimization theory and dual-time-scaled mechanism, proximal policy optimization algorithm based deep reinforcement learning was used to solve the connection relationship and offloading strategy of edge servers between fixed edge sink layer and mobile edge access layer.The simulation results show that, the proposed mechanism can reduce the service request delay and system energy consumption while ensuring the stability of system.…”
Get full text

Fuzzy Coordinated PI Controller: Application to the Real-Time Pressure Control Process by N. Kanagaraj, P. Sivashanmugam, S. Paramasivam

“…The proposed control algorithm is experimentally implemented for the real-time pressure control of a pilot air tank system and validated using a high-speed 32-bit ARM7 embedded microcontroller board (ATMEL AT91M55800A). …”
Get full text

Cluster-projected matrix product state: Framework for engineering exact quantum many-body ground states in one and two dimensions by Hidehiro Saito, Chisa Hotta

“…The key to find such a solution is a systematic protocol, which projects out excited states on every cluster using MPS and effectively entangles the cluster states. This algorithm not only offers an exact solution to general frustration-free Hamiltonian, but even provide the excited eigenstates by setting a proper target. …”
Get full text

Traffic classification in SDN-based IoT network using two-level fused network with self-adaptive manta ray foraging by Mohammed A. Aleisa

“…This paper presents a novel traffic classification framework for SDN-based IoT networks, introducing a Two-Level Fused Network integrated with a self-adaptive Manta Ray Foraging Optimization (SMRFO) algorithm. The framework automatically selects optimal features and fuses multi-level network insights to enhance classification accuracy. …”
Get full text