FPGA Acceleration With Hessian-Based Comprehensive Intra-Layer Mixed-Precision Quantization for Transformer Models by Woohong Byun, Jongseok Woo, Saibal Mukhopadhyay

“…To support this algorithm, we design a multi-precision FPGA accelerator capable of handling both 2n-based and non-2n mixed-precision operations. …”
Get full text

A Novel CPAP Device With an Integrated Oxygen Concentrator for Low Resource Countries: In Vitro Validation and Usability Test in Field by Sofia Poletto, Emanuela Zannin, Emanuele Ghilotti, Giovanni Putoto, Jerry Ichto, Peter Lochoro, Moses Obizu, Samuel Okori, Matteo Corno, Raffaele L Dellaca

“…<italic>Methods:</italic> The device integrates a blower-based ventilator and a portable oxygen concentrator. A novel control algorithm was designed to achieve the desired fraction of inspired oxygen (FiO₂) while minimizing power consumption. …”
Get full text

U-shaped relationship between frailty and non-HDL-cholesterol in the elderly: a cross-sectional study by Yu Pan, Yan Yuan, Juan Yang, Zhu Qing Feng, Xue Yin Tang, Yi Jiang, Gui Ming Hu, Jiang Chuan Dong

“…Non-HDL cholesterol levels in the range of 117.54–194.64 mg/dL were less likely to be frailty, while the likelihood of developing frailty was higher at 47.99–63.87 or 274.01–259.65 mg/dL. …”
Get full text

Controllability test for nonlinear datatic systems by Yujie Yang, Letian Tao, Likun Wang, Shengbo Eben Li

“…Starting with a specific target state, our algorithm can iteratively propagate controllability from a known state ball to a new one. …”
Get full text

Process parameter optimization of laser beam machining for AISI -P20 mold steel using ANFIS method by Abdullah Eaysin, Sarower Kabir, Ebru Gunister, Nur Jahan, Amir Hamza, Muhammad Ali Zinnah, Adib Bin Rashid

“…Based on the Brute Force algorithm, the minimum combination resulted in a kerf width of 0.84 mm and a surface roughness of 4.48175 μm. …”
Get full text

Discovering temporal, spatial, and contextual anomalous social activities from streaming social media datasets by Mete Celik, Ahmet Sakir Dokuz, Alper Ecemis, Emre Erdogmus

“…The results demonstrate that the proposed TSCASA-Miner algorithm outperforms the other algorithms, with a recall of 0.93, a precision of 0.95, and an accuracy of 0.9323, marking an improvement of 0.018 in accuracy.…”
Get full text

A Multi-Objective Gray Consistency Correction Method for Mosaicking Regional SAR Intensity Images with Brightness Anomalies by Jiaying Wang, Xin Shen, Deren Li, Litao Li, Yonghua Jiang, Jun Pan, Zezhong Lu, Wei Yao

“…To synchronously solve the truncation values of brightness anomaly images and linear stretch parameters of all images, a hybrid framework that combines the non-dominated sorting genetic algorithm II (NSGA-II) with the quadratic programming (QP) algorithm was proposed. …”
Get full text

An Optimization Coverage Strategy for Wireless Sensor Network Nodes Based on Path Loss and False Alarm Probability by Jianing Guo, Yunshan Sun, Ting Liu, Yanqin Li, Teng Fei

“…The model can achieve full coverage of the area with only 50 nodes, while the exponential decay model requires 54 nodes, and the coverage of the 0/1 model is still less than 70% at 60 nodes. …”
Get full text

Machine learning frameworks to accurately predict coke reactivity index by Ayat Hussein Adhab, Morug Salih Mahdi, Krunal Vaghela, Anupam Yadav, Jayaprakash B, Mayank Kundlas, Ankur Srivastava, Jayant Jagtap, Aseel Salah Mansoor, Usama Kadem Radi, Nasr Saadoun Abd, Samim Sherzod

“…To minimize overfitting in each algorithm, K-fold cross-validation methodology is employed during the training phase. …”
Get full text

Multi-Objective Optimization of UAV Relay Deployment for Air-to-Ground Communications via Distributed Collaborative Beamforming by Yang Yang, Xin Feng, Jing Zhang, Hongwei Yang, Tingting Zheng

“…The MOP aims to minimize the maximum sidelobe level (SLL) and propulsion energy consumption while maximizing the transmission rate. We propose an enhanced multi-objective evolutionary algorithm, BSINSGA-II, which integrates beetle swarm optimization (BSO) into the non-dominated sorting genetic algorithm II (NSGA-II). …”
Get full text

DSiam-CnK: A CBAM- and KCF-Enabled Deep Siamese Region Proposal Network for Human Tracking in Dynamic and Occluded Scenes by Xiangpeng Liu, Jianjiao Han, Yulin Peng, Qiao Liang, Kang An, Fengqin He, Yuhua Cheng

“…Building on this, we present DSiam-CnK, a Siamese neural network with dynamic template updating capabilities, facilitating adaptive adjustments in tracking strategy. The proposed algorithm is tailored to elevate the Siamese neural network’s accuracy and robustness for prolonged tracking, all the while preserving its tracking velocity. …”
Get full text

Monte Carlo Simulation and Experimental Validation for Radiation Protection with Multiple Complex Source Terms and Deep Penetration for a Radioactive Liquid Waste Cementation Facil... by Wenqian Li, Xuegang Liu, Sheng Fang, Xueliang Fu, Kaiqiang Guo

“…The complex shielding also leads to a deep penetration problem; hence, the optimization algorithm and variance reduction techniques were adopted. …”
Get full text

Green Apple Detection Method Based on Multidimensional Feature Extraction Network Model and Transformer Module by Wei Ji, Kelong Zhai, Bo Xu, Jiawen Wu

“…The test results show that the algorithm proposed in this article exhibits great potential in the task of detecting pollution-free near-color fruits by the picking robot. …”
Get full text

RF-PSignal: The Smart Home Gesture Recognition System Based on Channel-Wise Topology and Self-Adaptive Attention by Xiaohang Zhang, Chunhong Yue, Yajun Zhang, Kun Liang, Yanxiang Li

“…First, we fuse the signal phase and signal strength and propose a time-series-to-image algorithm to generate denoised images. Second, the system proposes three feature extraction modules designed based on the concept of channel topology, effectively improving recognition accuracy while reducing model complexity. …”
Get full text

Resource Allocation in User-Centric Cell-Free Massive MIMO URLLC Systems With Network Slicing by Han Lu, Weiwei Xia, Weiwei Miao, Mingxuan Zhang, Feng Yan, Lianfeng Shen

“…In this paper, we present a novel resource allocation scheme for network slicing based user-centric CF-mMIMO networks to maximize the achievable sum data rate while maintaining the quality of URLLC services. …”
Get full text

Connected Transit Bus Dynamic Priority Weight Modeling and Conflicting Request Resolution Control at the Signalized Intersection by Shuxian He, Haihang Han, Huan Zhang, Shanzhi Sun, Tony Z. Qiu

“…What is more, it shows better delay optimization for social vehicles than the algorithm with delay as the objective while declining bus delay appreciable quantity with 43.4 s in average. …”
Get full text

Toward sustainable machining of hardened SKD11: Machine learning-based evaluation and optimization of surface roughness, tool wear, and CO2 emissions by Van-Canh Nguyen, Dung Hoang Tien, Van-Hung Pham, Thinh-Viet Nguyen, Thuy-Duong Nguyen

“…Input variables comprise cutting speed (Vc), feed rate (fz), and cutting depth (ap), while output parameters include surface roughness (Ra), carbon emission (CE), and tool wear (Vb). …”
Get full text

Next-Generation Block Ciphers: Achieving Superior Memory Efficiency and Cryptographic Robustness for IoT Devices by Saadia Aziz, Ijaz Ali Shoukat, Mohsin Iftikhar, Mohsin Murtaza, Abdulmajeed M. Alenezi, Cheng-Chi Lee, Imran Taj

“…Moreover, comparative assessments reveal that our algorithm achieves a throughput of 853.31 Kbps while consuming only 1510 bytes of memory and demonstrating over 60% avalanche properties, significantly outperforming other solutions in terms of CPU utilisation and memory consumption. …”
Get full text

Advanced Hybrid Brain Tumor Segmentation in MRI: Elephant Herding Optimization Combined with Entropy-Guided Fuzzy Clustering by Baiju Karun, Arunprasath Thiyagarajan, Pallikonda Rajasekaran Murugan, Natarajan Jeyaprakash, Kottaimalai Ramaraj, Rakhee Makreri

“…EHO is utilized to optimize the clustering process, enhancing the algorithm’s ability to delineate tumor boundaries, while entropy-based fuzzy clustering accounts for intensity inhomogeneity and diverse tumor characteristics, promoting more consistent and reliable segmentation results. …”
Get full text

REDUCE—A Tool Supporting Inconsistencies Reduction in the Decision-Making Process by Paweł Kuraś, Dominik Strzałka, Bartosz Kowal, Patryk Organiściak, Krzysztof Demidowski, Veronika Vanivska

“…Quantitative evaluations demonstrate that REDUCE can improve matrices with high inconsistency (e.g., <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>C</mi><mi>R</mi><mo>=</mo><mn>0.25</mn></mrow></semantics></math></inline-formula>) to acceptable levels (e.g., <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>C</mi><mi>R</mi><mo>=</mo><mn>0.08</mn></mrow></semantics></math></inline-formula>) while retaining up to 95% of the original preference integrity, depending on the chosen algorithm. …”
Get full text