WANG Kechao, CAI Ruoyi, SHEN Jianjian · SHILAP Revista de lepidopterología · 2025
The coronavirus herd immunity optimizer (CHIO) algorithm was introduced to address the optimal scheduling problem of cascade hydropower plants, and an improved algorithm called LCHIO was proposed. The CHIO algorithm was enhanced by adopting two strategies: the Latin hypercube strategy for generating initial population solutions and dynamic social distance and adaptive threshold strategies. These improvements balanced global search and local search, preventing premature convergence while accelerating the convergence speed. Simulation results for four cascade hydropower plants in a region in southwest China show that the difference between the results of CHIO and LCHIO and the dynamic programming POA-DDDP is less than 1%, and the variation coefficients are 0.13% and 0.11%, which verify the rationality and effectiveness of CHIO to solve the cascade reservoir group scheduling problem and the improvement effect of LCHIO algorithm on CHIO. Further analysis of multiple objective function models for the equivalent grid reveals issues such as the coexistence of power shortages and curtailment, difficulties in renewable energy absorption, and weak generation capacity during dry periods. These challenges highlight the need for the development of pumped storage.
Cited by 0Open access
Jie Zhang, Fang Wang · Computational Intelligence and Neuroscience · 2022
Gestational diabetes mellitus (GDM) is one of the risk factors for fetal dysplasia and maternal pregnancy difficulties. Therefore, the prediction of the risk of GDM in advance has become a big demand for millions of families. Therefore, machine learning technology is adopted to study GDM prediction. Firstly, the data is preprocessed, and the mean value is used for outlier processing. After preprocessing of the data, the IV value method is used to screen the features. Of the 83 features in the original sample data, 40 important features are screened out through feature engineering. On this basis, Logistics regression model, Lasso-Logistics, Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (Xgboost), Light Gradient Boosting Machine (Lightgbm), and Gradient Boosting Categorical Features (Catboost) are established, and multiple learners are integrated. Finally, the constructed model is tested on data sets. The accuracy of the proposed model is 80.3%, the accuracy is 74.6%, the recall rate is 79.3%, and the running time is only 2.53 seconds. This means that the proposed model is superior to the previous models in terms of accuracy, precision, recall rate, and F1 value, and the time consumption is also in line with the actual engineering requirements. The proposed scheme provides some ideas for the research of machine learning technology in disease prediction.
Cited by 14Open access
Fuli Xu, Yu Wang, Yan Jiang et al. · 2023
Due to the interference of blurry background, character occlusion, and low background contrast in the Cast Pipe character images, the detection accuracy and real-time performance cannot meet the requirements of industrial scenes. To address these issues, this paper presents an improvement based on the Cascade Mask RCNN. Firstly, the Channel Attention Mechanism Module (Squeeze-and-Excitation, SE) is embedded into the ResNet structure. By constructing a bottleneck structure with two fully connected layers, the normalized weights are applied to each channel feature to enhance the network representation ability. Secondly, a bottom-up structure is introduced after the Feature Pyramid Networks (FPN) to transmit the strong localization information from lower-level features to higher-level semantic features. Thirdly, an adaptive pooling layer is added to allocate the candidate regions generated by the Region Proposal Network (RPN) to different scale feature maps. Additionally, skip connections are introduced between the bottom-level features and the highest-level features of each stage to reduce model parameters while retaining global representation capabilities. The improved algorithm is tested on a cast pipe dataset, achieving an average detection accuracy (mAP) of 98.7%, which is 2.7% higher than that of Cascade Mask RCNN. The accuracy indicates that the improved performance is superior to the original algorithm.
Cited by 0
Hongtao Wang, Changchun Xiao, Jialiang He et al. · 2025
This paper proposes a novel FIR filter implementation structure, which utilizes the conjugate reciprocal symmetry of the zeros of linear phase FIR filters to cascade decompose high-order FIR filters and ensure the linear phase characteristics of each cascaded sub-filter. In the article, the feasibility of the cascade decomposition algorithm is first derived and demonstrated to address the problem that the distributed arithmetic (DA) based on FPGA occupies too many lookup table (LUT) resources, and the design and implementation of the digital algorithm are analyzed in depth with examples. By reducing the order of high-order filters, the LUT resources are effectively saved and the operating frequency of FIR filters is improved. Finally, a general conclusion on the cascade decomposition algorithm for high-order FIR filters is presented, which has good engineering application value.
Cited by 0
Godem Ali M. Ismeal, Karol Kyslan, Viliam Fedák · Procedia Engineering · 2014
PID controller presents the most widely used controller in industrial applications. It needs efficient methods to set-up and tune parameters of its three components based on the properties of the plant and its parameters. In this paper the cascade controller for a DC drive (consisting of the speed and current controllers in series) is designed and tuned using genetic algorithm technique with different objective functions. The method of designing two PID controllers connected in cascade by the genetic algorithm technique was applied to a DC drive equipped by current and speed controllers. The aim of genetic algorithm control method consists in finding the best set of solutions for the controller parameters that give desired dynamic and static performance of the system. By using MATLAB/Simulink software a graphical user interface (GUI) was developed for efficiently, user friendly, and comfortable calculation and tuning the parameters of both controllers in cascade and for visualizing results.
Cited by 6Open access
Mikhail S. Jadzhak · Journal of Automation and Information Sciences · 2004
The algorithm of parallel-pipeline numerical solution of the spatial problem of multiphase cascade digital filtration is proposed. The conditions of optimality of this algorithm by an operating speed, in the class of algorithms equivalent by an information graph, are given.
Cited by 5
Rong Luo, Jing Wen Li, Shu CHeng Zhang · 2021
The definition of edge-magic total labeling is that the sum of any edge and its associated points in a graph is equal to a certain constant, and the set satisfied by the value of midpoint and edge is from the number of one edge to the sum of the number of edges and points. In this paper, we design an edge-magic total labeling algorithm based on the hierarchical cascade graph. By using the edgemagic total labeling algorithm, we can get the super edgemagic total labeling of the hierarchical cascade graph. Through research and analysis, it is obtained that the join graph composed of hierarchical cascade graph, its extended graph and some special graphs is super edgemagic total labeling, super set-ordered edge-magic total labeling. Some theorems are summarized and proved.
Cited by 0
V. E. Bunakov, G. V. Matvejev · The European Physical Journal A · 1985
Cited by 17
Benjamin Decardi‐Nelson, Jinfeng Liu · 2022 American Control Conference (ACC) · 2022
In this work, we present a distributed framework based on the graph algorithm for computing control invariant set for nonlinear cascade systems. The proposed algorithm exploits the structure of the interconnections within a process network. First, the overall system is decomposed into several subsystems with overlapping states. Second, the control invariant set for the subsystems are computed in a distributed manner. Finally, an approximation of the control invariant set for the overall system is reconstructed from the subsystem solutions and validated. We demonstrate the efficacy and convergence of the proposed method to the centralized graph-based algorithm using a nonlinear example.
Cited by 0
Sujata Gaikwad, Upendra Patil, Mansi Subhedar · 2023
The proposed work is developed to avoid accidents caused due to different parameters and aims to build an effective system. Design modifications are not required in vehicle, this work can be externally placed in vehicle so all old vehicles can be part of this system. Emphasizing the aspects that make commuting a laborious job and providing appropriate solutions to make the journey safe and reliable is crucial in improving the overall commuting experience. The proposed system covers two aspect - First aspect determine driver's drowsiness which will determine the sleeping and yawning state of the driver. The system automatically detects driver fatigue based on visual information and artificial intelligence. Identifying, tracking and analyzing both the driver's face and eyes and using softmax of neuron transfer functions measures PERCLOS (percentage of eyes closed).Second aspect includes adaptive cruise system which includes sensors. The sensor used in this system is not reliant on human visual perception, distance judgment, or directional awareness. Instead, it monitors the driving environment and identifies potential dangerous situations. It handles various tasks such as preventing collisions while reversing, maintaining a safe distance from the vehicle in front, avoiding collisions at intersections, avoiding obstacles on the road, and keeping the vehicle within its lane. To achieve real-time monitoring, the system utilizes the Raspberry Pi Camera. The methods proposed in this work, such as feature extraction and neural networks, help to overcome the drawbacks of the current approaches, increase the effectiveness of traffic sign detection, and decrease the number of accidents on the road.
Cited by 2
FENG Lei, JIANG Lei, XU Hua, GOU Zezhong · SHILAP Revista de lepidopterología · 2021
The recognition accuracy of traditional modulation recognition algorithms based on deep learning is reduced in the case of small sample size.To solve the problem,this paper proposes a small sample modulation recognition algorithm for communication signal based on deep cascade Siamese network.Firstly,according to the spatial and temporal features of the sequence diagram of communication signals,the feature extraction module cascaded by Convolutional Neural Network(CNN) and Long Short Term Memory(LSTM) network is designed to map the original signal features to the feature space.At the same time,the extracted features are measured under the Siamese network architecture,and train the network with similarity constraints to avoid the problem of over fitting in the training.Finally,the modulation category of the to be tested samples is identified through the nearest neighbor classifier.Results of experiments on the public modulation dataset DeepSig show that compared with the traditional modulation recognition algorithms based on deep learning,the proposed algorithm can significantly reduce the number of samples required in training,and the recognition accuracy is higher under small sample conditions.
Cited by 0Open access
Shaohua Li · 2006
In this paper, the author propose a new hash algorithm called cascade hashes. It uses three levels of hash tables, and higher level hashes work as fail-safes of lower level hashes. By this strategy, it could effectively reduce collisions in hash insertion. Thus it gains a constant worst case lookup time with a relatively high load factor(70%-80%) in random experiments. The mathematical basis is also analyzed. 1
Cited by 0
Wei Ji, Hongde Jiang, Ruixian Cai · Volume 1: Turbomachinery · 1987
A fast effective Multi-grid algorithm for calculating 2-D transonic cascade flow governed by full-potential equation is presented in this paper. Numerical results obtained show the powerful effect of the method in both accelerating convergence and improving accuracy. In addition, according to the conservation of potential equations, a reasonable treatment for cascade leading edge calculation in H-type grid is also presented.
Cited by 0
Haoxuan wang, Yasong Luo, Zhong Liu · 2024
Surface unmanned platforms can realize the purpose of attacking the enemy boats by loading counterload. In order to solve the problem of maximally traumatizing the enemy boats under the premise of limited damage capability, a cascade detection algorithm for key parts of boats based on YOLOv7 is proposed. Firstly, the detection strategy is reconstructed, and the detection of the key parts of boats is divided into two stages. The cascade detection algorithm is designed to detect the whole boats first and then the key parts. Secondly, the boats dataset NSDS and the key parts dataset NSKPDS are constructed. Thirdly, considering that multiple boats targets may be detected in the first stage, a multithreaded design is introduced in the second stage. And the relevant control experiments are carried out. The results show that the multithreaded design can effectively shorten the detection time of the cascade detection algorithm. Finally, the proposed cascade detection algorithm, YOLOv7, YOLOv5 and YOLOv8 algorithms are tested on the constructed datasets. And the results show that the cascade detection algorithm can not only effectively complete the detection of key parts of boats, but also has a higher total detection rate and average confidence than other detection algorithms.
Cited by 0
Md Fakhrul Islam (9806711) · Figshare · 2005
Artificial Neural Network (ANN) based tap changer control of closed primary bus and cross network connected parallel transformers has demonstrated potential use in power distribution system [1– 3]. In those research works the proposed ANN for application in this control were developed using various algorithms and concluded that a network trained by Bayesian Regularization (BR) backpropagation algorithm produced the best performance measured in terms of correct tap changing decisions. However, further improvement of ANN based transformer tap changer operation is always desirable. A general rule for obtaining good generalization is to use the smallest network that solves the problem [4]. In this paper, we show that a small sized ANN is obtainable for further improvement of transformer tap changer operation by modifying the standard Cascade-Correlation algorithm. The modification incorporates weight smoothing of output layer weights in Cascade-Correlation learning using Bayesian frame work. Experimental results demonstrate that significant improvement in performance is achieved when an ANN is trained by modified Cascade-Correlation algorithm instead of standard Cascade-Correlation or Bayesian Regularization backpropagation algorithm. A comparison of performances of different algorithms in application to transformer tap changer operation is analyzed and the results are presented.
Cited by 0Open access
Amira Sersar, Mohammed B. Debbat · Communications in computer and information science · 2023
Cited by 0
Wei Zhao, Li Ying Wang · Advanced materials research · 2010
The cascade correlation algorithm that is cascade-correlation(CC) algorithms, CC network structure and CC network weights learning algorithm are introduced, based on the real data in hydropower station, considering the cavitation characteristics, the network model is established based on CC algorithm, and the applications of CC and BP algorithm of turbine are compared. The results show that the CC algorithm is better than BP neural network, the results can be used in the optimal operation of hydropower, and it has a practical significance.
Cited by 0
А.В. Антонова, Vadim P. Nikolaenko, V.V. Brzheskiy · Russian Journal of Clinical Ophthalmology · 2021
Aim: to analyze the duration and regimen of topical treatment and the pattern of prior laser and surgical procedures in patients with glaucoma who were admitted to the hospital for IOP-lowering interventions. Patients and Methods: this study included 500 consecutively enrolled patients who underwent surgery for uncontrolled glaucoma in 2016– 2020 and were followed up for 6–24 months. Disease history, cumulative "preservative" load, clinical examinations, and surgical outcomes were assessed. Results: preoperatively, most patients received the maximum medical therapy (i.e., three agents in two bottles). Simultaneous use of all four major classes of IOP-lowering medications occurred in 10% of patients only. Two-third of patients required surgical interventions to reduce IOP after a 6-year medical therapy. By the time of admission, 60% of patients were diagnosed with advanced or end-stage glaucoma. Prior laser or surgical procedures to reduce IOP were performed only in 142 patients and 52 patients, respectively. Treatment adherence was lower in men compared to women, irrespective of its stage. Conclusion: most patients received adequate medical therapy. However, in general, surgery was performed too late. It gives the impression that the efficacy of therapeutic and laser stages of cascade glaucoma treatment is no more than five years. In addition to the obvious drawbacks of a laissez-faire strategy (irreversible vision loss), the risk of surgical failure significantly increases. Long-term (at least 3-year) therapy using (non)fixed-dose combinations of agents containing preservatives is the major modifiable risk factor for early filtration loss. Preservativefree prostaglandin analogues improve treatment tolerability, adherence to treatment, and chances for success of IOP-lowering surgery. The authors’ results demonstrate that gender differences should be considered when planning treatment and follow-up visits. Keywords: glaucoma, IOP-lowering therapy, glaucoma surgery, ocular surface, preservatives, benzalkonium chloride. For citation: Antonova A.V., Nikolaenko V.P., Brzheskiy V.V. Realization of a cascade treatment algorithm for glaucoma in St. Petersburg. Russian Journal of Clinical Ophthalmology. 2021;21(3):123–128 (in Russ.). DOI: 10.32364/2311-7729-2021-21-3-123-128.
Cited by 6Open access
Chang Su, Na Xu, Fang Zhou et al. · Chinese Physics B · 2025
Abstract Independent cascade (IC) models, by simulating how one node can activate another, are important tools for studying the dynamics of information spreading in complex networks. However, traditional algorithms for the IC model implementation face significant efficiency bottlenecks when dealing with large-scale networks and multi-round simulations. To settle this problem, this study introduces a GPU-based parallel independent cascade (GPIC) algorithm, featuring an optimized representation of the network data structure and parallel task scheduling strategies. Specifically, for this GPIC algorithm, we propose a network data structure tailored for GPU processing, thereby enhancing the computational efficiency and the scalability of the IC model. In addition, we design a parallel framework that utilizes the full potential of GPU’s parallel processing capabilities, thereby augmenting the computational efficiency. The results from our simulation experiments demonstrate that GPIC not only preserves accuracy but also significantly boosts efficiency, achieving a speedup factor of 129 when compared to the baseline IC method. Our experiments also reveal that when using GPIC for the independent cascade simulation, 100–200 simulation rounds are sufficient for higher-cost studies, while high precision studies benefit from 500 rounds to ensure reliable results, providing empirical guidance for applying this new algorithm to practical research.
Cited by 0
Guo Juan, Hao Guocheng, Li Xiangbo et al. · Mechanical Systems and Signal Processing · 2025
Cited by 0