A smarter approach to liquefaction risk: harnessing dynamic cone penetration test data and machine learning for safer infrastructure by Shubhendu Vikram Singh, Sufyan Ghani

“…ML models, including Support Vector Machine (SVM) optimized with Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), Genetic Algorithm (GA), and Firefly Algorithm (FA), were employed to predict the e/qd ratio using key geotechnical parameters, such as fine content, peak ground acceleration, reduction factor, and penetration rate. …”
Get full text

Empirical Evaluation on GPU, Overclocking, and LoRA for Deep Learning on Embedded Systems by Evandro Raphaloski, Mariana Caravanti De Souza, Edson Takashi Matsubara

“…The trade-offs between reducing training time, image throughput, accuracy loss, temperature increase, and power consumption were analyzed using two strategies: 1) overclocking and 2) low-rank adaptation (LoRA). …”
Get full text

6G virtualized beamforming: a novel framework for optimizing massive MIMO in 6G networks by Ahmed M. Alwakeel

“…Furthermore, the system incorporates predictive analytics for proactive beam steering and user allocation, enhancing network performance while minimizing power consumption. Simulation results show a 22% reduction in power consumption and a 19% increase in spectral efficiency compared to traditional beamforming approaches. …”
Get full text

Effectiveness of biomarker-guided duration of antibiotic treatment in children hospitalised with confirmed or suspected bacterial infection: the BATCH RCT by Cherry-Ann Waldron, Philip Pallmann, Simon Schoenbuchner, Debbie Harris, Lucy Brookes-Howell, Céu Mateus, Jolanta Bernatoniene, Katrina Cathie, Saul N Faust, Josie Henley, Lucy Hinds, Kerry Hood, Chao Huang, Sarah Jones, Sarah Kotecha, Sarah Milosevic, Helen Nabwera, Sanjay Patel, Stéphane Paulus, Colin VE Powell, Jenny Preston, Huasheng Xiang, Emma Thomas-Jones, Enitan D Carrol

“…Children aged between 72 hours and 18 years admitted to hospital and being treated with IV antibiotics for suspected or confirmed bacterial infection were randomised (1 : 1 ratio of allocation) using minimisation for age and centre and using a secure 24-hour web-based randomisation programme to a PCT-guided algorithm versus usual standard care alone. The sample size of 1942 was determined, based on detecting a 1-day reduction in IV antibiotic use (90% power, two-sided) and on a non-inferiority margin of 5% absolute risk difference (RD) in the composite safety outcome (90% power, one-sided), while allowing for up to 10% loss to follow-up. …”
Get full text

Towards Secure IoT Authentication System Based on Fog Computing and Blockchain Technologies to Resist 51% and Hijacking Cyber-Attacks by Muwafaq Jawad, Ali A. Yassin, Hamid Ali Abed Al-asadi, Zaid Ameen Abduljabbar, Vincent Omollo Nyangares, Zaid Alaa Hussien, Husam A. Neamah

“…Despite its significant benefits for modern smart healthcare, IoHT faces growing security challenges due to the limited processing power, storage capacity, and self-defense capabilities of its devices. …”
Get full text

Efficient Stereo Visual Odometry on FPGA Featuring On-Chip Map Management and Pipelined Descriptor-Based Block Matching by Yuki Ichikawa, Kazushi Kawamura, Masato Motomura, Thiem van Chu

“…These advancements result in significant reduction in off-chip data transfer, memory savings, and faster processing times. …”
Get full text

Sparse Deep Neural Network for Encoding and Decoding the Structural Connectome by Satya P. Singh, Sukrit Gupta, Jagath C. Rajapakse

“…We show that relevancy score-based methods can yield high discriminative power and are suitable for brain decoding. We also show that the proposed approach led to a reduction in the number of trainable network parameters, an increase in classification accuracy, and a detection of brain connections and regions that were consistent with earlier studies.…”
Get full text

Cooperate or Not Cooperate: Transfer Learning With Multi-Armed Bandit for Spatial Reuse in Wi-Fi by Pedro Enrique Iturria-Rivera, Marcel Chenier, Bernard Herscovici, Burak Kantarci, Melike Erol-Kantarci

“…Simulation results show that cooperation via the SAU-Coop algorithm leads to a 14.7% improvement in cumulative throughput and a 32.5% reduction in Packet Loss Rate (PLR) in comparison to non-cooperative approaches. …”
Get full text

FinSafeNet: securing digital transactions using optimized deep learning and multi-kernel PCA(MKPCA) with Nyström approximation by Ahmad Raza Khan, Shaik Shakeel Ahamad, Shailendra Mishra, Mohd Abdul Rahim Khan, Sunil Kumar Sharma, Abdullah AlEnizi, Osama Alfarraj, Majed Alowaidi, Manoj Kumar

“…MKPCA seeks to analyze and understand a non-linear structure of data whereas, Nyström Approximation reduces the burden on computational power hence allows the model to work in situations where large sizes of datasets are available but with no loss of efficiency of the model. …”
Get full text

Optimization of microwave-assisted polyphenol extraction and antioxidant activity from papaya peel using response surface methodology and artificial neural network by Md. Waziur Rahman Chy, Tanvir Ahmed, Junaid Iftekhar, Md. Zohurul Islam, Md. Rahmatuzzaman Rana

“…The objective of the present study is to determine the optimal conditions of microwave-assisted extraction (MAE) such as microwave power (MWP), irradiation time (I-time), ethanol concentration (EtOH%), and solvent-to-solid ratio (S/S) for maximizing total polyphenol content (TPC) and 2,2-diphenyl-1-picrylhydrazyl (DPPH) radical scavenging activity from papaya peel. …”
Get full text

Predictive Study on the Cutting Energy Efficiency of Dredgers Based on Specific Cutting Energy by Junlang Yuan, Ke Yang, Taiwei Yang, Haoran Xu, Ting Xiong, Shidong Fan

“…First, eigenvalue screening is carried out based on the dredging knowledge and mechanism, then outliers are removed, and finally data processing is performed using Spearman correlation coefficient and PCA dimensionality reduction techniques. Subsequently, five machine learning algorithms, such as RF and XGBoost, are used in combination with a grid search to find the optimal hyperparameters, and Lasso is used as the meta-learner to integrate the prediction results. …”
Get full text

Synergistic Effects of Energy Storage Systems and Demand-Side Management in Optimizing Zero-Carbon Smart Grid Systems by Zeyad A. Almutairi, Ali M. Eltamaly

“…An advanced optimization algorithm enhances grid stability and efficiency. Simulations demonstrate significant reductions in carbon footprint, peak power demand, and reliance on fossil fuels. …”
Get full text

Energy management system for PV-based distributed generators in AC microgrids using an adapted JAYA optimizer to minimize operational costs, energy losses, and CO2 emissions by Nicolás Ignacio Labra-Cáceres, Luis Fernando Grisales-Noreña, Rubén Iván Bolaños, Jhony Andrés Guzmán-Henao, Oscar Danilo Montoya

“…To solve the model, an adapted version of the JAYA optimization algorithm was implemented, and its performance was compared against four established methodologies: the Chu & Beasley Genetic Algorithm (CBGA), Particle Swarm Optimization (PSO), the Vortex Search Algorithm (VSA), and Ant Lion Optimization (ALO). …”
Get full text

Optimization of engine parameters and emission profiles through bio-additives: Insights from ANFIS Modeling of Diesel Combustion by Abbas Rohani, Javad Zareei, Kourosh Ghadamkheir, Seyed Alireza Farkhondeh

“…Various machine learning configurations and training algorithms were employed to optimize the model's performance. …”
Get full text

Prediction of Aluminum Alloy Surface Roughness Through Nanosecond Pulse Laser Assisted by Continuous Laser Paint Removal by Jingyi Li, Rongfan Liang, Han Li, Junjie Liu, Jingdong Sun

“…A back propagation neural network (BPNN) coupled with a sparrow search algorithm (SSA) is employed to predict surface roughness. …”
Get full text

A novel obfuscation method based on majority logic for preventing unauthorized access to binary deep neural networks by Alireza Mohseni, Mohammad Hossein Moaiyeri, Mohammad Javad Adel

“…The proposed approach yields 43%, 79%, and 71% reductions in area, average power, and weight modification energy per filter in the neural network structures. …”
Get full text

Modeling, optimization, and thermal management strategies of hydrogen fuel cell systems by Abubakar Unguwanrimi Yakubu, Liu Qingsheng, Meng Kai, Chen Jinwei, Omer Abbaker Ahmed Mohammed, Jiahao Zhao, Qi Jiang, Xuanhong Ye, Junyi Liu, Qinglong Yu, Muhammad Aurangzeb, Shusheng Xiong

Get full text

Bitcoin price direction prediction using on-chain data and feature selection by Ritwik Dubey, David Enke

“…To address the curse of dimensionality, feature selection algorithms such as L1 regression, Boruta, and the dimensionality reduction algorithm Principal Component Analysis (PCA) are utilized. …”
Get full text

Optimal design of solar cells grid electrodes based on quadratic curves by Yongjiang Liu, Kai Li, Bo Zhou, Xiangquan Li, Peizheng Li

“…This paper presents an optimization methodology employing width-varying quadratic curves to parameterize grid electrode profiles, coupled with a comprehensive power loss model. A genetic algorithm (GA) is implemented to minimize total power loss, systematically optimizing grid designs for solar cells with 156 × 156 mm², 182 × 182 mm², and 210 × 210 mm². …”
Get full text

Computational design exploration of rocket nozzle using deep reinforcement learning by Aagashram Neelakandan, Arockia Selvakumar Arockia Doss, Natrayan Lakshmaiya

“…Deep Reinforcement Learning (DRL) has emerged as a powerful tool for solving high-dimensional optimization problems in complex, unexplored domains. …”
Get full text