Multi-exit Kolmogorov–Arnold networks: enhancing accuracy and parsimony by James Bagrow, Josh Bongard

“…This architecture provides deep supervision that improves training while discovering the right level of model complexity for each task. …”
Get full text

Forced Oscillation Detection via a Hybrid Network of a Spiking Recurrent Neural Network and LSTM by Xiaomei Yang, Jinfei Wang, Xingrui Huang, Yang Wang, Xianyong Xiao

“…The proposed hybrid network is trained using the backpropagation-through-time (BPTT) optimization algorithm, with adjustments made to address the discontinuous gradient in the SRNN. …”
Get full text

A Preventive-Corrective Scheme for Ensuring Power System Security During Active Wildfire Risks by Satyaprajna Sahoo, Anamitra Pal

“…The results obtained using the IEEE 118-bus system indicate that the proposed approach alleviates system vulnerabilities to wildfires while also minimizing operational cost.…”
Get full text

An Efficient Anomalous Sound Detection System for Microcontrollers by Yi-Cheng Lo, Tsung-Lin Tsai, Chieh-Wen Yang, An-Yeu Wu

“…Therefore, we propose a memory-aware pruning algorithm specialized for ASD to fit into MCUs’ constraints. …”
Get full text

Dynamic Control and Analysis of Dual Active Bridge Converters in Grid-Connected PV-BESS by Mehmet Can Sekanli, Samet Yalçin, Okan Bingol

“…The Perturb & Observe (P&O) Maximum Power Point Tracking (MPPT) algorithm optimized power extraction from the PV array, while the DAB converter employed Single Phase Shift (SPS) control for efficient, bidirectional energy management. …”
Get full text

An Efficient Method for Offset Mitigation in Free-Space Optical Systems by Omar A. Saraereh, Imran Khan, Jeong Woo Lee

“…With the increase of dc offset <italic>d</italic>, the system error rate is significantly reduced and more approaching <italic>d</italic> &#x003D; 0 (i.e., no dc offset). The proposed algorithm effectively mitigates the dc offset impact on the system and the BER is significantly improved while the MSE is reduced to 50&#x0025; of the traditional state-of-the-art method. …”
Get full text

Designing a glycemic control strategy to maintain glucose homeostasis and prevent hypoglycemia for subjects with type 1 diabetes by A. Rafie Lak, O. Vahidi

“…To obtain the second tuning set, the controller parameters are optimized through a sequential quadratic programming algorithm. …”
Get full text

Integrating feedback control for improved human-structure interaction analysis by Santiago A. Lopez, Daniel Gomez, Albert R. Ortiz, Sandra Villamizar

“…While well-established in robotics and automation engineering, these control algorithms represent a novel and transformative approach when applied to HSI. …”
Get full text

Advanced thermal management in radiology equipment: Numerical and semi-analytical analysis of flat heat pipes by Maryam Johari, Hossein Ali Hoshyar, Davood Domiri Ganji

“…Advanced techniques—specifically the Least Squares Method (LSM) and the fourth-order Runge-Kutta-Fehlberg (RKF) algorithm, are employed to conduct a comprehensive analytical investigation of heat pipe performance. …”
Get full text

Machine Learning Innovations for Improving Mineral Recovery and Processing: A Comprehensive Review* by Korie, Josephmartin Izuchukwu*, Chudi-Ajabor, Ogochukwu Gabriela, Ezeonyema, Chukwudalu Chukwuekezie, Oshim, Francisca Ogechukwu

“…While challenges persist, such as limited data availability, non-normally distributed and non-linear data, and varying data dimensions and rates, the advantages of employing ML algorithms are undeniable. …”
Get full text

Uninterrupted Connectivity Using Conditional Time Split Energy Extraction With Beamforming System for Disaster Affected Wireless Networks by K. Ashok, T. Sudha

“…Promising beamforming (BF) architecture with Conditional Time split-Energy Extraction (CT-EE) is proposed to maximize the Energy Efficiency while optimizing the Mean Square Error (MSE) and Achievable Sum Rate (ASR). …”
Get full text

Efficient Material Flow and Storage Space Determination in Automated Distribution Centers by Mohammed Alnahhal, Nikola Gjeldum, Mohammed Ruzayqat

“…Items with relatively large demand levels have scenario 3 as the optimal one. Results also showed that the model reduces both total costs and stacker crane utilization while improving system flexibility.…”
Get full text

“Bias Correction Method” for Regional Correction Experiment of Warm Season Rainstorm in Zhejiang by Chengyan Mao, Xin Pan, Haowen Li, Weibiao Li, Haoya Liu

“…This study employs the K-means clustering algorithm to partition warm-season precipitation in Zhejiang Province into distinct regions. …”
Get full text

Short-Term Power Prediction for Wind Farm and Solar Plant Clusters Based on Machine Learning Method by Yang CUI, Zhenghong CHEN, Peihua XU

“…Firstly, the machine learning-based Bisecting K-Means(BKM) clustering algorithm is used to reasonably divide the wind farms and PV stations in the region into clusters; Secondly, based on the correlation between of the historical power data of each power station and the total historical power data in the region, a representative power station is selected for each region; Thirdly, after optimizing and correcting the NWP(numerical weather prediction) model of each representative power station, a short-term power prediction framework model is established using BP neural network based on the cluster division of wind farms and PV power plants. …”
Get full text

Educational frontiers with ChatGPT: a social network analysis of influential tweets by Mehmet Firat, Saniye Kuleli

“…Using the ForceAtlas2 algorithm and thematic content analysis, the study explores the appeal of ChatGPT and its prospects as an educational tool. …”
Get full text

SATELLITE ALTIMETER DATA FILTERING AND SMOOTHING IN THE COURSE OF GROUND-BASED RETRACKING by D. S. Borovitsky, A. E. Zhesterev, V. P. Ipatov, R. M. Mamchur

“…The paper subject is study of retracking algorithms of altimeter data transmitted from the space vehicle to the ground segment.Methods and materials. …”
Get full text

QuantumGS-Box—A Key-Dependent GA and QRNG-Based S-Box for High-Speed Cloud-Based Storage Encryption by Anish Saini, Athanasios Tsokanos, Raimund Kirner

“…In this paper, we propose the QuantumGS-box, which is a dynamic S-box for high-speed cloud-based storage encryption generated by bit shuffling with a genetic algorithm and a quantum random number generator (QRNG). …”
Get full text

DIGEST: Fast and Communication Efficient Decentralized Learning With Local Updates by Peyman Gholami, Hulya Seferoglu

“…Gossip algorithms (both synchronous and asynchronous versions) suffer from high communication cost, while random-walk based learning experiences increased convergence time. …”
Get full text

The Impact of Road Functions on Road Congestions Based on POI Clustering: An Empirical Analysis in Xi’an, China by Hui Zhu, Kaiqi Zhang, Changjun Wang, Lujin Jia, Siyu Song

“…We adopted the DBSCAN algorithm to cluster POIs and use the mixed POI clusters to label the socio-economic functions of roads. …”
Get full text

Sensitivity analysis of factors influencing the curve negotiation performance of hot metal train by TIAN Mingjie, HUANG Zhihui, CHEN Xuejing, YANG Quan, YU Hongda

“…Track irregularities have the greatest influence on the safety of train curve operation, followed by curve radii and curve superelevations, while running speeds exhibit little influence.…”
Get full text