Zixuan Wu¹, Ye Wang^1,*, Lifeng Shen², Feng Hu¹, Hong Yu^1,*

CMC-Computers, Materials & Continua, Vol.80, No.3, pp. 4111-4127, 2024, DOI:10.32604/cmc.2024.054581 - 12 September 2024

Abstract Hierarchical Text Classification (HTC) aims to match text to hierarchical labels. Existing methods overlook two critical issues: first, some texts cannot be fully matched to leaf node labels and need to be classified to the correct parent node instead of treating leaf nodes as the final classification target. Second, error propagation occurs when a misclassification at a parent node propagates down the hierarchy, ultimately leading to inaccurate predictions at the leaf nodes. To address these limitations, we propose an uncertainty-guided HTC depth-aware model called DepthMatch. Specifically, we design an early stopping strategy with uncertainty to More >

Sanxiu Jiao¹, Lecai Cai^2,*, Jintao Meng³, Yue Zhao³, Kui Cheng²

Computer Systems Science and Engineering, Vol.48, No.1, pp. 247-265, 2024, DOI:10.32604/csse.2023.040194 - 26 January 2024

Abstract Federated learning is a distributed machine learning framework that solves data security and data island problems faced by artificial intelligence. However, federated learning frameworks are not always secure, and attackers can attack customer privacy information by analyzing parameters in the training process of federated learning models. To solve the problems of data security and availability during federated learning training, this paper proposes an Efficient Differential Privacy Federated Learning Algorithm based on early stopping mechanism (Efficient DP-FL). This method inherits the advantages of differential privacy and federated learning and improves the performance of model training while More >

Ramanjaneyulu Kolla^*, Vinayagasundaram Ganesh, Rajendran Sakthivel, Arumugam Kumar Boobalasenthilraj

Computer Systems Science and Engineering, Vol.45, No.3, pp. 3115-3134, 2023, DOI:10.32604/csse.2023.033077 - 21 December 2022

Abstract The braking quality is considered the main execution of the adaptive control framework that impacts the vehicle safety and rides solace astoundingly notably the stopping distance. This research work aims to create a pattern and design of an electromechanically adjusted lever that multiplies the applied braking force depending on the inputs given by the sensors to reduce the stopping distance of the vehicle. It is carried out using two main parts of the two-wheeler vehicle: the first part deals with the detection of load acting on the vehicle and identifying the required braking force to… More >

Y. L. Zhang^a , H. B. Lin^b, S. P. Li^b,*, J. J. Xiao^a, L. Zhang^c

Frontiers in Heat and Mass Transfer, Vol.18, pp. 1-6, 2022, DOI:10.5098/hmt.18.47

Abstract Centrifugal pumps need to be stopped in the case of closing valve sometimes due to some specific application requirements. This paper presents a numerical simulation of the unsteady flow inside a low specific speed centrifugal pump during closed-valve forward and reverse stopping process. The study results show that the average internal pressure gradually decreases during stopping periods. At the same blade radius, the pressure on working surface is significantly higher than the suction surface. The pressure gradually increases from the impeller inlet to the outlet. The simulation fully shows the transient flow characteristics inside the More >

Phyu Hnin Thike^{1, 2}, Zhaoyang Zhao¹, Peng Liu¹, Feihu Bao¹, Ying Jin¹, Peng Shi^{1, *}

CMC-Computers, Materials & Continua, Vol.65, No.3, pp. 2091-2109, 2020, DOI:10.32604/cmc.2020.011608 - 16 September 2020

Abstract The optimization of network topologies to retain the generalization ability by deciding when to stop overtraining an artificial neural network (ANN) is an existing vital challenge in ANN prediction works. The larger the dataset the ANN is trained with, the better generalization the prediction can give. In this paper, a large dataset of atmospheric corrosion data of carbon steel compiled from several resources is used to train and test a multilayer backpropagation ANN model as well as two conventional corrosion prediction models (linear and Klinesmith models). Unlike previous related works, a grid searchbased hyperparameter tuning… More >