Ensemble machine learning-based pre-trained annotation approach for scRNA-seq data using gradient boosting with genetic optimizer by Osama Elnahas, Waleed M. Ead, Yushan Qiu, Jian Lu

“…We propose an ensemble machine learning-based pre-trained annotation framework that integrates gradient boosting and genetic optimization for robust feature selection. The proposed method uses ensemble learning to enhance annotation accuracy under data scarcity, addressing limitations in existing supervised methods by leveraging a combination of multiple annotated datasets and feature alignment strategies. …”
Get full text

Robust two stages federated learning for sensor based human activity recognition with label noise by Haifeng Sun, Junping Yao, Xiaojun Li, Yanfei Liu, Hongyang Gu

“…To overcome these challenges of complex label noise and feature drift, this paper proposes LN-FHAR, a two-stage federated learning framework with label noise robustness. …”
Get full text

Deep Neural Network-Based Detection of Modulated Jamming in Free-Space Optical Systems: Theory and Performance Under Atmospheric Fading by Manav R. Bhatnagar

“…This paper investigates the problem of detecting structured optical jamming introduced via a separate FSO link, where both legitimate and adversarial transmissions undergo independent Gamma-Gamma fading. …”
Get full text

The Development of a Lightweight DE-YOLO Model for Detecting Impurities and Broken Rice Grains by Zhenwei Liang, Xingyue Xu, Deyong Yang, Yanbin Liu

“…The loss problem of class imbalance is optimized using the Focal Loss function. …”
Get full text

Dynamic convolutional model based on distribution-collaboration strategy for remote sensing scene classification by Chenjun Xu, Jingqian Shu, Zhenghan Wang, Jialin Wang

“…Secondly, an adaptive enhanced attention mechanism based on the Lie Group feature covariance matrix is designed to aggregate the essential attribute feature (EAF) of HRRSI, which can effectively deal with HRRSI without increasing the computational complexity and delay of the model with the increase of HRRSI resolution. …”
Get full text

A hybrid approach of vision transformers and CNNs for detection of ulcerative colitis by Syed Abdullah Shah, Imran Taj, Syed Muhammad Usman, Syed Nehal Hassan Shah, Ali Shariq Imran, Shehzad Khalid

“…Researchers have proposed variety of machine/deep learning methods for automated detection of ulcerative colitis, however, several challenges exists including class imbalance problem, comprehensive feature extraction and accurate classification. …”
Get full text

Neural Machine Translation in Electrical Engineering With Cross-Layer Information Fusion and Multiple Positional Mapping by Zhenyu Zhang, Yuan Chen, Juwei Zhang

“…This method integrates the Long Short-Term Memory (LSTM) and the attention mechanism to construct a cross-layer information compensation architecture consisting of a cross-layer feature propagation module and a feature fusion module to compensate for the attenuation of cross-layer semantic information and position information. …”
Get full text

Effectiveness of using a slider-crank mechanism for waffle background milling by I. N. Drozdov, A. Yu. Popov

“…This eliminates the exit of the mechanism out of the cell dimensions, as well as provides a significant reduction of cutting forces up to 10 N and removes the problem of using coolant (dry machining). This is a feature of the high-speed milling mode, when the feed rate and cutting speed are significantly higher than traditional ones, and the cutting depth does not exceed 1 mm. …”
Get full text

Fault Diagnosis of Semi-Supervised Electromechanical Transmission Systems Under Imbalanced Unlabeled Sample Class Information Screening by Chaoge Wang, Pengpeng Jia, Xinyu Tian, Xiaojing Tang, Xiong Hu, Hongkun Li

“…This mechanism discriminates based on the variability of intrinsic feature information in fault samples, accurately screening out unlabeled samples located near decision boundaries that are difficult to separate clearly. …”
Get full text

Bayesian Optimized Enhanced Ensemble Multi-Layer Perceptron for Rear-End Collision Prediction in IoV by Dilna Vijayan, Mohamed Saad, Ahmed M. Khedr

“…The complexity entailed in tackling this problem, specifically concerning the prediction of rear-end crashes, demands the application of cutting-edge methodologies. …”
Get full text

A Cloud User Anomaly Detection Method Based on Mouse Behavior by XU Hong-jun, ZHANG Hong, HE Wei

“… Aiming at the problem of cloud security threat caused by illegal operation of cloud users, this paper proposes a method to detect the abnormal behavior of cloud users by analyzing the mouse operation behavior in user’s work by using deep learning technology under the premise of ensuring the privacy of cloud users. …”
Get full text

FAULT DIAGNOSIS OF SCRAPER CONVEYOR REDUCER BASED ON IMPROVED FIREFLY ALGORITHM TO OPTIMIZE NEURAL NETWORK by MAO Jun, GUO Hao, CHEN HongYue

“…The second application feature data sample for fault diagnosis model based on neural network training. …”
Get full text

Parallel and distributed chimp-optimized LSTM for oil well-log reconstruction in China by Zisong Wang, Zhiliang Cheng, Wenxiang Wang, Xiujian Ding, Lu Xia

“…This study tackles this problem by devising a deep Long Short-Term Memory (LSTM) model that uses the new Parallel and Distributed Chimp Optimization Algorithm (PDCOA). …”
Get full text

Object Tracking with Adaptive Multicue Incremental Visual Tracker by Jiang-tao Wang, De-bao Chen, Jing-ai Zhang, Su-wen Li, Xing-jun Wang

“…Generally, subspace learning based methods such as the Incremental Visual Tracker (IVT) have been shown to be quite effective for visual tracking problem. However, it may fail to follow the target when it undergoes drastic pose or illumination changes. …”
Get full text

Offline Handwritten Chinese Character Recognition Based on DBN and CNN Fusion Model by LI Lanying, ZHOU Zhigang, CHEN Deyun

“…Aiming at the problem that some offline handwritten Chinese characters are similar in shape and it is difficult to extract the feature of characters and the recognition is not accurate, a convolutional neural network and deep belief network fusion model is proposed Firstly, the convolutional neural network and the deep belief network are trained on the dataset respectively It is found that the comprehensive TOP-2 accuracy of the both can reach 99.33% Using the advantages of convolutional neural networks and deep belief networks in image analysis, a fusion comparison strategy is adopted to extract a classification result as accurately as possible in the TOP-2 classification of the two to improve the recognition ability The experimental results show that the fusion model of convolutional neural network and deep belief network has better recognition effect than convolutional neural network and deep belief network…”
Get full text

Fuzzy Volterra Integral Equations with Piecewise Continuous Kernels: Theory and Numerical Solution by S. Noeiaghdam, D.N. Sidorov, A.I. Dreglya

“…This research focuses on addressing both linear and nonlinear fuzzy Volterra integral equations that feature piecewise continuous kernels. The problem is tackled using the method of successive approximations. …”
Get full text

Underwater Localization and Tracking of Physical Systems by Patrick Carroll, Shengli Zhou, Hao Zhou, Xiaoka Xu, Jun-Hong Cui, Peter Willett

“…We investigate the problem of localizing an underwater sensor node based on message broadcasting from multiple surface nodes. …”
Get full text

Asymptotic second moment of Dirichlet L-functions along a thin coset by Bradford Garcia, Matthew P. Young

“…The lower-order main term does not appear in the second moment of the Riemann zeta function, so this feature is not anticipated from the analogous archimedean moment problem.…”
Get full text

Efficient DDoS attack detection and prevention scheme based on SDN in cloud environment by Heng HE, Yan HU, Lianghan ZHENG, Zhengyuan XUE

“…For addressing the problem of two typical types of distributed denial of service (DDoS) attacks in cloud environment,a DDoS attack detection and prevention scheme called SDCC based on software defined network (SDN) architecture was proposed.SDCC used a combination of bandwidth detection and data flow detection,utilized confidence-based filtering (CBF) method to calculate the CBF score of packets,judged the packet of CBF score below the threshold as an attacking packet,added its attribute information to the attack flow feature library,and sent the flow table to intercept it through SDN controller.Simulation results show that SDCC can detect and prevent different types of DDoS attacks effectively,and it has high detection efficiency,reduces the controller’s computation overhead,and achieves a low false positive rate.…”
Get full text

A Novel Rotating Disk System for Disintegration of Excess Sludge by Ming yang Zhang, Yun Xiang, Jian wei Du

“…Special feature on surfaces of disks had been proved to be a novel improvement which can improve disintegration effect apparently. …”
Get full text