Enhancing BVR Air Combat Agent Development With Attention-Driven Reinforcement Learning by Andre R. Kuroswiski, Annie S. Wu, Angelo Passaro

“…We propose a novel approach that introduces a task-based layer, leveraging domain expertise to optimize decision-making and training efficiency. By integrating multi-head attention mechanisms into the policy model and employing an improved DQN algorithm, agents dynamically select context-aware tasks, enabling the learning of efficient emergent behaviors for variable engagement conditions. …”
Get full text

A novel re-entrant circular star-shaped auxetic honeycomb with enhanced energy absorption and anisotropic Poisson’s ratio by Danrong Shi, Zhuangzhuang Wang, Yongwei Li, Ruyuan Huo, Jin Zhang, Jianguo Cai

“…A multi-objective optimisation strategy was used by a Kriging surrogate model and NSGA-II algorithm to identify an optimal configuration with improved crashworthiness. …”
Get full text

A Blur-Score-Guided Region Selection Method for Airborne Aircraft Detection in Remote Sensing Images by Yujian Wang, Yi Hou, Yuting Xie, Ruofan Wang, Shilin Zhou

“…Our approach includes an improved tenengrad gradient algorithm to extract motion blur information and construct a Blur-Score map. …”
Get full text

MATE-ViT: A multi-channel contrast-limited adaptive time-frequency enhancement and vision transformer framework for bearing fault diagnosis by Jiangdong Zhao, Jiao Yu, Wenming Wang, Ji Huang, Xiaolu Ma

“…First, an improved CLAHE algorithm is used to independently enhance the multi-channel time-frequency images, effectively improving the local contrast and detail expression of the images, thereby enhancing the recognizability of fault features. …”
Get full text

A data driven approach to urban area delineation using multi source geospatial data by Chenyu Fang, Lin Zhou, Xinyue Gu, Xing Liu, Martin Werner

“…Abstract This study introduces a data-driven, bottom-up approach to urban delineation, integrating feature engineering with the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, which represents a significant improvement in precision and methodology compared to traditional approaches that rely on simplistic OpenStreetMap (OSM) road node data aggregations. …”
Get full text

Dual-Metric-Based Assessment and Topology Generation of Urban Airspace with Quadrant Analysis and Pareto Ranking by Weizheng Zhang, Hua Wu, Yang Liu, Suyu Zhou, Hailong Dong, Huayu Liu

“…Additionally, Pareto ranking determines a set of Pareto-optimal solutions wherein no objective can be improved without compromising at least one other objective. …”
Get full text

An Advanced Recomposition-Based Displaying Technique: Maximizing Image Reconstruction for Virtual Museum Applications by Jingjie Zhao, Xin Shi, Olga Yezhova, Qinchuan Zhan, Xijing Zhang

“…These methods, combined with a multi-layer aggregation algorithm that encodes deep feature representations in a Gaussian Mixture Model (GMM), enable seamless scene reconstruction with improved precision. …”
Get full text

Spatiotemporal tensor analysis for effective information mining of hydraulic structures considering environmental excitation and vibration response by Hui Li, Zhang Han, Tengfei Bao, Xiaohan Duan, Guang Yang, Xianyu Xiong, Yibo Ouyang, Jiankang Lou

“…The time-weighted modified dynamic time warping theory and curvature smoothing algorithm were combined to construct the optimal filter model with a balancing factor to extract the effective information from vibration response. …”
Get full text

MAT-FHE: arbitrary dimension matrix multiplication scheme for floating point over fully homomorphic encryption by Yatao Yang, Zhaofu Li, Yucheng Ding, Man Hu

“…After analysis, it is secure under the CPA model, composable, and supports floating matrix continuous multiplication. …”
Get full text

Optimasi Algoritma Naive Bayes dengan Diskritisasi K-Means pada Diagnosis Penyakit Jantung by Nafa Fajriati, Budi Prasetiyo

“…Naïve Bayes is a classification algorithm that has a fairly good ability to build a classifier model. …”
Get full text

Online variational Gaussian process for time series data by Weidong Wang, Mian Muhammad Yasir Khalil, Leta Yobsan Bayisa

“…Unlike traditional methods that rely on a fixed number of inducing points, OLVGP adaptively adjusts the number of inducing points as new data arrives and optimizes them from the model, ensuring that the model remains computationally efficient while maintaining high predictive accuracy. …”
Get full text

Drowsiness Detection of Construction Workers: Accident Prevention Leveraging Yolov8 Deep Learning and Computer Vision Techniques by Adetayo Olugbenga Onososen, Innocent Musonda, Damilola Onatayo, Abdullahi Babatunde Saka, Samuel Adeniyi Adekunle, Eniola Onatayo

“…This study presents a vision-based approach using an improved version of the You Only Look Once (YOLOv8) algorithm for real-time drowsiness exposure among construction workers. …”
Get full text

Inversion of Leaf Chlorophyll Content in Different Growth Periods of Maize Based on Multi-Source Data from “Sky–Space–Ground” by Wu Nile, Su Rina, Na Mula, Cha Ersi, Yulong Bao, Jiquan Zhang, Zhijun Tong, Xingpeng Liu, Chunli Zhao

“…This study proposes an improved method based on multi-source data, combining the Sentinel-2A spectral response function (SRF) and computer algorithms, to overcome the limitations of traditional methods. …”
Get full text

Research on Hyperspectral Inversion of Soil Organic Carbon in Agricultural Fields of the Southern Shaanxi Mountain Area by Yunhao Han, Bin Wang, Jingyi Yang, Fang Yin, Linsen He

“…The results indicate that (1) the Spectral Space Transformation (SST) algorithm effectively eliminates environmental interference on image spectra, enhancing SOC prediction accuracy; (2) continuous wavelet transform significantly reduces data noise compared to other spectral processing methods, further improving SOC prediction accuracy; and (3) among feature band selection methods, the CARS algorithm demonstrated the best performance, achieving the highest SOC prediction accuracy when combined with the random forest model. …”
Get full text

Efficiency Design of Traction Inverters Based on Deep Learning and TRIZ by LIAGN Kaiwei, JIAO Bi, LIU Yongjiang, LING Zhenjun, SU Li, XIE Haibo

“…In addition, this paper designs human-computer interaction software based on TRIZ-CRNN to improve the operation intelligence of computer aided innovation system and optimize the application feasibility of TRIZ-CRNN algorithm.…”
Get full text

VR interactive input system based on INS and binocular vision fusion by Hongxia Zhao, Bei Wang

“…This study explores the application of inertial measurement units and binocular vision fusion technology in virtual reality interactive input systems, with the aim of improving the tracking accuracy of the system through optimized pose models and visual algorithms. …”
Get full text

Machine learning based assessment of hoarseness severity: a multi-sensor approach centered on high-speed videoendoscopy by Tobias Schraut, Anne Schützenberger, Tomás Arias-Vergara, Melda Kunduk, Matthias Echternach, Stephan Dürr, Julia Werz, Michael Döllinger

“…Subjects were classified into two hoarseness groups based on auditory-perceptual ratings, with predicted scores serving as continuous hoarseness severity ratings. A videoendoscopic model was developed by selecting a suitable classification algorithm and a minimal-optimal subset of glottal parameters. …”
Get full text

Mixed Gas Detection and Temperature Compensation Based on Photoacoustic Spectroscopy by Sun Chao, Hu Runze, Liu Niansong, Ding Jianjun

“…It determines the weight ratio of each algorithm through experiments to improve the accuracy of gas category discrimination. …”
Get full text

IoT intrusion detection method for unbalanced samples by ANTONG P, Wen CHEN, Lifa WU

“…In recent years, network traffic increases exponentially with the iteration of devices, while more and more attacks are launched against various applications.It is significant to identify and classify attacks at the traffic level.At the same time, with the explosion of Internet of Things (IoT) devices in recent years, attacks on IoT devices are also increasing, causing more and more damages.IoT intrusion detection is able to distinguish attack traffic from such a large volume of traffic, secure IoT devices at the traffic level, and stop the attack activity.In view of low detection accuracy of various attacks and sample imbalance at present, a random forest based intrusion detection method (Resample-RF) was proposed, which consisted of three specific methods: optimal sample selection algorithm, feature merging algorithm based on information entropy, and multi-classification greedy transformation algorithm.Aiming at the problem of unbalanced samples in the IoT environment, an optimal sample selection algorithm was proposed to increase the weight of small samples.Aiming at the low efficiency problem of random forest feature splitting, a feature merging method based on information entropy was proposed to improve the running efficiency.Aiming at the low accuracy problem of random forest multi-classification, a multi-classification greedy transformation method was proposed to further improve the accuracy.The method was evaluated on two public datasets.F1 reaches 0.99 on IoT-23 dataset and 1.0 on Kaggle dataset, both of which have good performance.The experimental results show that the proposed model can effectively identify the attack traffic from the massive traffic, better prevent the attack of hackers on the application, protect the IoT devices, and thus protect the related users.…”
Get full text

Design of Low-Power, High-Precision, and Lightweight Image Recognition System for Multiple Scenes by Gangfeng Yang, Liming Chen, Jianhua Jiang, Chengying Chen, Xindong Huang

“…Aiming at the existing handwritten digit recognition systems with low recognition accuracy, high system power consumption, and high hardware resource consumption, this paper proposes a low-power, high-precision, and lightweight handwritten digit recognition hardware acceleration scheme for multiscenario based on FPGA. By optimizing the network structure of a convolutional neural network (CNN) and the number of parameters of the model, this scheme proposes a high-precision and lightweight network model, simplified CNN, and by optimizing the data access mode and memory usage, and by adopting the strategies of time-sharing and multiplexing, weights sharing, and parallel processing for the hardware acceleration of the algorithm, it effectively reduces the consumption of hardware resources and improves the performance of the system. …”
Get full text