Optimal Network Structure Research Articles

Multiperiod optimization of cooling water system with flexible topology network

Cooling water systems (CWSs) are extensively utilized in various industries to eliminate the excess heat and converse energy. Studies on CWSs mainly concentrated on finding the optimal cooler network structure. In addition, some works also considered the optimal design under varied operation conditions. However, in these works, once the optimal design of the cooler's network is determined, its arrangement remains fixed and cannot be adapted to accommodate diverse operating conditions. In this work, a flexible topology network concept is proposed to make the adjustment of network structure possible under different operation conditions. The CWS with integrated air cooler and flexible topology network has better overall performance, represented by a mixed integer nonlinear programming (MINLP) model that require advanced tools such as GAMS software. Case studies revealed that the proposed methodology can realize better energy-saving performance, and improve the economic performance under varied operation conditions. The impact of critical flexible nodes on system configuration and economy is achieved by sensitivity analysis.

An automatic defect classification and segmentation method on three-dimensional point clouds for sewer pipes

With the development of deep learning (DL), sewer pipe inspection on two-dimensional (2D) images has achieved remarkable accuracy. However, extracting defect measurements from these 2D images is challenging due to the curved nature of pipes and the lack of depth information. Point clouds can restore the three-dimensional (3D) information of objects. To effectively identify defects in disordered and sparse point clouds, a 3D sewer pipe classification and segmentation method was proposed. In the encoder, the original point clouds are sampled and grouped and the local features in the clusters are extracted by two symmetric functions (1 × 1 convolution and the maximization function) to process the points with permutation invariance. In the decoder, the multi-scaling abstract features are upsampled using feature pyramid network (FPN) to predict the category of each point. Especially, the network structure and training strategy of the inspection method is optimized to improve the inspection accuracy. Furthermore, two data augmentation methods, namely random scaling and point jitter, are used to increase the data volume. An ablation experiment shows that the optimization of network structure can effectively improve the performance of the inspection model and the novel training strategies can stabilize the training process and prevent overfitting. Comparison among the state-of-the-art networks demonstrates that the proposed segmentation model attains the highest mIoU of 94.15 %, which is improved by 11.46 % with the optimization of network structure and training strategy. For the classification task, the F1 score and accuracy of the established model are 6.79 % and 5.46 % higher than PointNet++, respectively. These results signify the high-accuracy defect inspection capability of our proposed method on 3D point clouds of sewer pipelines.

Inter-organizational collaboration after institutional reform in China: A perspective based on the revision of the emergency plan

In an era marked by increasingly complex risks and extreme disasters, nations are progressively leaning towards inter-organizational collaboration as a means to adapt and respond effectively. Guided by the principles of holistic governance and comprehensive emergency management, the establishment of comprehensive coordination institutions has emerged as a vital strategy for enhancing a country’s emergency response capabilities. Nevertheless, the transformation of inter-organizational cooperation networks following institutional reform remains shrouded in ambiguity. This research, employing a blend of quantitative and qualitative analyses within a network theory framework, delves into the shifts within inter-organizational cooperation networks subsequent to institutional reform. By scrutinizing the evolution of emergency plan networks at provincial, municipal, and county levels before and after China’s institutional reform and drawing insights from emergency plan revision personnel, this study unveils a noteworthy trend. Specifically, the inter-organizational collaboration network in China’s emergency management sector has gravitated towards a unified command model, fostering heightened cross-functional cooperation and optimizing network structure. The findings of this study not only shed light on the post-reform dynamics of inter-organizational cooperation networks in China but also offer valuable insights for other countries and regions seeking to develop effective emergency management systems. As the global landscape continues to evolve, understanding and adapting to these changes in network dynamics becomes imperative for bolstering disaster response capabilities worldwide.

Self-optimization wavelet-learning method for predicting nonlinear thermal conductivity of highly heterogeneous materials with randomly hierarchical configurations

In the present work, we propose a self-optimization wavelet-learning method (SO-W-LM) with high accuracy and efficiency to compute the equivalent nonlinear thermal conductivity of highly heterogeneous materials with randomly hierarchical configurations. The randomly structural heterogeneity, temperature-dependent nonlinearity and material property uncertainty of heterogeneous materials are considered within the proposed self-optimization wavelet-learning framework. Firstly, meso- and micro-structural modeling of random heterogeneous materials are achieved by the proposed computer representation method, whose simulated hierarchical configurations have relatively high volume ratio of material inclusions. Moreover, temperature-dependent nonlinearity and material property uncertainties of random heterogeneous materials are modeled by a polynomial nonlinear model and Weibull probabilistic model, which can closely resemble actual material properties of heterogeneous materials. Secondly, an innovative stochastic three-scale homogenized method (STSHM) is developed to compute the macroscopic nonlinear thermal conductivity of random heterogeneous materials. Background meshing and filling techniques are devised to extract geometry and material features of random heterogeneous materials for establishing material databases. Thirdly, high-dimensional and highly nonlinear material features of material databases are preprocessed and reduced by wavelet decomposition technique. The neural networks are further employed to excavate the predictive models from dimension-reduced low-dimensional data. At the same time, advanced intelligent optimization algorithms are utilized to self-search the optimal network structure and learning rate for obtaining the optimal predictive models. Finally, the computational accuracy and efficiency of the presented approach are validated via various numerical experiments on realistic random composites.

BNSL GOBNILP algorithm in application to damage intensity prognostic system to RC multistorey residential buildings subjected to negative impacts of the industrial environment of mines

Paper presents a method of predicting the damage intensity of multifamily prefabricated RC buildings located in the range of impacts of the industrial environment of mines. The research studied the effects of mining impacts in the form of large-scale continuous ground deformation and mining tremors. For this purpose, in-situ data collected in the database was used. Additional information in the database included: structural and material features, quality of maintenance and durability of the analysed buildings. Finally, a predictive model represented by an optimal Bayesian network structure was created. To obtain the optimal topology of the DAG network structure, a Bayesian network learning algorithm from data GOBNILP was adapted. According to this algorithm, the optimisation process was carried out through Gurobi Optimizer. Thus, the conducted analyses represent the first time the above-mentioned approach has been applied in the interdisciplinary field of civil and environmental engineering. As part of the analyses, the available metric scores were verified and multiple network structures were examined according to their complexity. This made it possible to select the best Bayesian network in terms of generalizing the knowledge acquired while learning its structure. The possibility of using the obtained model for issues of diagnosis of damage causes and their prediction was also presented.

Influence of Time-Series Length and Hyperparameters on Temporal Convolutional Neural Network Training in Low-Power Battery SOC Estimation

In battery management systems, state of charge (SOC) estimation is important for ensuring the safety and reliability of batteries. Currently, there are various methods for estimating SOC, and the neural network method is the most popular. However, when the battery’s SOC is low (below 20%), the uncertainty in neural network parameters can lead to significant bias in SOC estimation. To address these problems, this study proposes a method based on genetic algorithm (GA) optimization of a time-serialization convolutional neural network (TSCNN) model. First, the population is initialized according to the optimized hyperparameters of the TSCNN model, whereby the experimental data are converted into time-series data. Subsequently, neural network models are built based on the population, thereby using the effect of the network as the fitness function for GA optimization. Finally, an optimized network structure is obtained for accurate SOC estimation. During the optimization process, the optimized data exhibited abnormal phenomena, usually manifested as exceeding the data limits or being zero. In the past, abnormal data were discarded and new data were regenerated; however, this reduces the correlation between data. Therefore, this study proposes a check function to enhance the correlation between the data, converting abnormal data into normal data by limiting the data range. To the best of our knowledge, it is the first time that a GA is being proposed to optimize the time-series length of a convolutional neural network (CNN) while the neural network parameters are optimized so that the time-series length and neural network parameters achieve the best match. In the experimental results, the maximum error was 4.55% for the dynamic stress test (DST) dataset and 2.58% for the urban dynamometer driving schedule (UDDS) dataset. When the battery SOC was below 20%, the estimation error did not incur a huge error. Therefore, the optimization method proposed for the TSCNN model in this study can effectively improve the accuracy and reliability of SOC estimation in the low-battery state.

CSANet: a channel-spatial attention network for remote sensing image change detection

ABSTRACT Deep learning has revolutionized change detection (CD) in remote sensing tasks. However, high-resolution CD based on deep learning faces challenges in handling semantic complexity in bi-temporal images, especially across varying weather and lighting conditions. While CNN-based approaches optimize network structures to enhance contextual information, recent attention-based methods increase computational demands. This study introduces the Channel-Spatial Attention Network (CSANet) to extract multi-scale and semantic information from images. Evaluated on LEVIR-CD and DSIFN-CD datasets, CSANet outperforms several state-of-the-art methods, demonstrating its potential for advanced change detection in high-resolution remote sensing.

Optimization of artificial neural network structure and hyperparameters in hybrid model by genetic algorithm: iOS–android application for breast cancer diagnosis/prediction

Optimization of artificial neural network structure and hyperparameters in hybrid model by genetic algorithm: iOS–android application for breast cancer diagnosis/prediction

Image Processing Method of a Visual Communication System Based on Convolutional Neural Network

Unmanned motion platforms are being used in a wide range of industries. Unmanned motion platforms must have an autonomous and intelligent navigation procedure in order to carry out their system functions. Traditional inertial navigation and radio navigation have poor accuracy and autonomy when not dependent on satellite circumstances. The accuracy of image recognition algorithms must meet strict standards. This study and exploration of the high-precision scene image recognition system is based on convolutional neural network structure optimization. To demonstrate the viability of the approach, simulation experiments are carried out on the NUC dataset using the recognition technique based on a convolutional neural network that is proposed. The fundamental network architecture of a convolutional neural network is optimized using the L2 regularization technique. The experimental findings demonstrate that the NUC dataset now has better recognition accuracy. In terms of recognition accuracy, the suggested method satisfies the predetermined requirements.

Neural network structure optimization for Hefei Light Source II β function correction

In this study, we address the design challenges related to hyperparameters, such as the number of layers and nodes in deep neural networks, by introducing an Improved Genetic Algorithm-based method for optimizing neural network structures (IGA-DNN). We apply this method to the practical problem of β function correction in particle accelerators and develop a storage ring β function correction scheme based on IGA-DNN. We compare our approach with traditional genetic algorithm-optimized neural networks to evaluate its performance. Our results reveal that the neural network optimized by the improved genetic algorithm reduces the number of layers by three and decreases training time by a factor of three, leading to a more efficient model. Moreover, the accuracy of β function simulation correction is enhanced using the IGA-DNN method. This approach can also be extended to optimize other optical parameters and tackle multi-parameter optimization problems, showcasing its versatility and potential for broader applications across various fields.

Predicting Severe Haematological Toxicity in Gastrointestinal Cancer Patients Undergoing 5-FU-Based Chemotherapy: A Bayesian Network Approach.

Severe toxicity is reported in about 30% of gastrointestinal cancer patients receiving 5-Fluorouracil (5-FU)-based chemotherapy. To date, limited tools exist to identify at risk patients in this setting. The objective of this study was to address this need by designing a predictive model using a Bayesian network, a probabilistic graphical model offering robust, explainable predictions. We utilized a dataset of 267 gastrointestinal cancer patients, conducting preprocessing, and splitting it into TRAIN and TEST sets (80%:20% ratio). The RandomForest algorithm assessed variable importance based on MeanDecreaseGini coefficient. The bnlearn R library helped design a Bayesian network model using a 10-fold cross-validation on the TRAIN set and the aic-cg method for network structure optimization. The model's performance was gauged based on accuracy, sensitivity, and specificity, using cross-validation on the TRAIN set and independent validation on the TEST set. The model demonstrated satisfactory performance with an average accuracy of 0.85 (±0.05) and 0.80 on TRAIN and TEST datasets, respectively. The sensitivity and specificity were 0.82 (±0.14) and 0.87 (±0.07) for the TRAIN dataset, and 0.71 and 0.83 for the TEST dataset, respectively. A user-friendly tool was developed for clinical implementation. Despite several limitations, our Bayesian network model demonstrated a high level of accuracy in predicting the risk of developing severe haematological toxicity in gastrointestinal cancer patients receiving 5-FU-based chemotherapy. Future research should aim at model validation in larger cohorts of patients and different clinical settings.

AutoEER: automatic EEG-based emotion recognition with neural architecture search

Objective. Emotion recognition based on electroencephalography (EEG) is garnering increasing attention among researchers due to its wide-ranging applications and the rise of portable devices. Deep learning-based models have demonstrated impressive progress in EEG-based emotion recognition, thanks to their exceptional feature extraction capabilities. However, the manual design of deep networks is time-consuming and labour-intensive. Moreover, the inherent variability of EEG signals necessitates extensive customization of models, exacerbating these challenges. Neural architecture search (NAS) methods can alleviate the need for excessive manual involvement by automatically discovering the optimal network structure for EEG-based emotion recognition. Approach. In this regard, we propose AutoEER (Automatic EEG-based Emotion Recognition), a framework that leverages tailored NAS to automatically discover the optimal network structure for EEG-based emotion recognition. We carefully design a customized search space specifically for EEG signals, incorporating operators that effectively capture both temporal and spatial properties of EEG. Additionally, we employ a novel parameterization strategy to derive the optimal network structure from the proposed search space. Main results. Extensive experimentation on emotion classification tasks using two benchmark datasets, DEAP and SEED, has demonstrated that AutoEER outperforms state-of-the-art manual deep and NAS models. Specifically, compared to the optimal model WangNAS on the accuracy (ACC) metric, AutoEER improves its average accuracy on all datasets by 0.93%. Similarly, compared to the optimal model LiNAS on the F1 Ssore (F1) metric, AutoEER improves its average F1 score on all datasets by 4.51%. Furthermore, the architectures generated by AutoEER exhibit superior transferability compared to alternative methods. Significance. AutoEER represents a novel approach to EEG analysis, utilizing a specialized search space to design models tailored to individual subjects. This approach significantly reduces the labour and time costs associated with manual model construction in EEG research, holding great promise for advancing the field and streamlining research practices.

Research On Emergency Parcel Transfer and Structure Optimization of E-Commerce Logistics Network Based on Multi-Objective Planning

This paper addresses the problem of urgent forwarding and structural optimization of parcels in e-commerce logistics networks. Firstly, based on the historical data of past freight volumes of different routes, this paper predicts the freight volume forecast data of each route by establishing an ARIMA time series forecast model; secondly, a multi-objective optimization model based on genetic algorithm is established to derive the optimal freight volume allocation scheme after the disappearance of route DC5; again, a multi-objective optimization model based on bat algorithm is established to derive the DC9 route Finally, a multi-objective optimization model based on the bat algorithm was developed to derive the route adjustment and cargo allocation scheme after the disappearance of route DC9. This paper concludes that after the cancellation of the DC5 route, the number of routes that are not in normal operation is 23 and the number of logistics paths that are allocated to new cargo is 56 in order to achieve the most balanced route load possible; after the closure of the DC9 route, 21 new roads are opened and 15 roads are closed, which are in a normal flow state and the transhipment is balanced. This paper has more far-reaching applications for multi-objective large-scale NP problems by establishing a multi-objective optimization model based on a heuristic algorithm, which can reduce the solution time of the calculation.

Neural Modelling in the Study of the Relationship between Herd Structure, Amount of Manure and Slurry Produced, and Location of Herds in Poland

In the presented study, data regarding the size and structure of cattle herds in voivodeships in Poland in 2019 were analysed and modelled using artificial neural networks (ANNs). The neural modelling approach was employed to identify the relationship between herd structure, biogas production from manure and slurry, and the geographical location of herds by voivodeship. The voivodeships were categorised into four groups based on their location within Poland: central, southern, eastern, and western. In each of the analysed groups, a three-layer MLP (multilayer perceptron) with a single hidden layer was found to be the optimal network structure. A sensitivity analysis of the generated models for herd structure and location within the eastern group of voivodeships revealed significant contributions from dairy cows, heifers (both 6–12 and 12–18 months old), calves, and bulls aged 12–24 months. For the western voivodeships, the analysis indicated that only dairy cows and herd location made significant contributions. The optimal models exhibited similar values of RMS errors for the training, testing, and validation datasets. The model characterising biogas production from manure in southern voivodeships demonstrated the smallest RMS error, while the model for biogas from manure in the eastern region, as well as the model for slurry in central parts of Poland, yielded the highest RMS errors. The generated ANN models exhibited a high level of accuracy, with a fitting quality of approximately 99% for correctly predicting values. Comparable results were obtained for both manure and slurry in terms of biogas production across all location groups.

Variable Neighborhood Search Algorithm for the Single Assignment Incomplete Hub Location Problem with Modular Capacities and Direct Connections

In distribution systems such as airlines and express package delivery, the use of hub-and-spoke networks is common, and flow consolidation at hub facilities is essential for cost reduction. While a constant discount factor is typically used to model cost reduction in interhub links, this paper explores an extension of the incomplete hub location problem with modular capacity that enables direct connections between non-hub nodes. The modified approach, called MHLPDC, aims to locate a set of hub facilities, connect each non-hub node to a hub, and activate hub facility links, access arc links, and direct links between non-hub nodes to minimize network costs. The MHLPDC integrates link activation decisions into the decision-making process and utilizes modular arc costs to model the flow dependence of transportation costs in all arcs. To solve the problem, the paper presents a mixed-integer mathematical programming formulation and heuristic algorithm based on a greedy randomized adaptive search and variable neighborhood search approach. The proposed algorithm produces high-quality solutions, as demonstrated through computational experiments on benchmark instances with up to 40 nodes. Furthermore, a sensitivity analysis of the optimal network structure indicates that increasing the discount factor, by varying hub and access arc capacities as well as the associated variable costs, results in fewer hubs being established and more direct shipments between non-hub nodes being permitted.

Robustness of Double-Layer Group-Dependent Combat Network with Cascading Failure

The networked combat system-of-system (CSOS) is the trend of combat development with the innovation of technology. To achieve the combat effectiveness, studying the ability of CSOS to cope with external interference is of great importance. Here we report a modeling method of CSOS from the perspective of complex networks and explore the robustness of the combat network based on this. Firstly, a more realistic double-layer heterogeneous dependent combat network model is established. Then, the conditional group dependency situation is considered to design failure rules for dependent failure, and the coupling relation between the double-layer subnets is analyzed for overload failure. Based on this, the initial load and capacity of the node are defined, respectively, as well as the load redistribution strategy and the status judgment rules for the cascading failure model. Simulation experiments are carried out by changing the attack modes and different parameters, and the results show that the robustness of the combat network can be effectively improved by improving the tolerance limit of one-way dependency of the functional net, the node capacity of the functional subnet, and the tolerance of the overload state. The conclusions of this paper can provide a useful reference for network structure optimization and network security protection in the military field.

Enhancement of ISPP Efficiency Using Neural Network-Based Optimization of 3-D NAND Cell

The enhancement of program efficiency is essential for fast NAND cell operation. However, it is difficult to simultaneously consider many factors, such as structural parameters and trap characteristics, having complex relationships. To overcome these problems, we proposed a neural network (NN)-applied optimization method. First, an optimal network structure was selected by comparing the network performance and learning time. The selected network accurately predicted the threshold voltages of the 21 states of a single NAND cell within a second. Next, an optimization method to improve program efficiency is suggested. The improved NAND cell structure is obtained using a trained NN and numerical method. Here, the optimization required only a few minutes for one optimization process and could consider all parameters simultaneously. Finally, the optimized NAND cell was evaluated using a technology computer-aided design (TCAD) simulation, and its program efficiency was verified. This study shows a specific example of machine learning applied to the semiconductor area, especially in NAND flash memory.

Research on Workpiece Intelligent Detection Method Based on SSD Algorithm and Transfer Learning

For the robot intelligent manufacturing workshop, the intelligent detection of workpiece products is the basis for efficient management and precision detection of production lines, which is of great significance for the reliable operation of intelligent manufacturing unmanned production lines. Therefore, SSD algorithm and migration learning in deep learning is studied to sorting the workpieces in this paper. Firstly, based on the five workpieces of screw, nut, gasket, spring, and gear, the multi-workpiece detection data set of the intelligent production line is constructed. Secondly, the multi-scale features of different workpieces are extracted by deep convolution network SSD. Then, the migration learning method is applied to complete the migration network training of workpiece intelligent detection, so the small data detection accuracy is obtained. Finally, after transfer learning solidifying and pruning the transfer learning training model, It is deployed to the embedded terminal Invidia Jetson Nano to realize the online intelligent detection. The experimental results show that the workpiece detection accuracy reaches 99% based on SSD network migration learning. After the network structure optimization pruning embedded deployment, the workpiece detection accuracy is better than 86%, and the frame rate is more than 7FPS. So the proposed method can realize five kinds of workpieces intelligent detection on unmanned production lines.

Single and Multiple Separate LSTM Neural Networks for Multiple Output Feature Purchase Prediction

Data concerning product sales are a popular topic in time series forecasting due to their multidimensionality and wide presence in many businesses. This paper describes the research in predicting the timing and product category of the next purchase based on historical customer transaction data. Given that the dataset was acquired from a vendor of medical drugs and devices, the generic product identifier (GPI) classification system was incorporated in assigning product categories. The models built are based on recurrent neural networks (RNN) and long short-term memory (LSTM) neural networks with different input and output features, and training datasets. Experiments with various datasets were conducted and optimal network structures and types for predicting both product category and next purchase day were identified. The key contribution of this research is the process of data transformation from its original purchase transaction format into a time series of input features for next purchase prediction. With this approach, it is possible to implement a dedicated personalized marketing system for a vendor.

A hybrid approach for forecasting bitcoin series

Bitcoin price prediction is a substantial challenge for cryptocurrency investors. This study offers an innovative scheme to predict Bitcoin returns and volatilities using a hybrid model that incorporates the autoregressive fractionally integrated moving average (ARFIMA), empirical wavelet (EW) transform, and local linear wavelet neural network (LLWNN) approaches to produce an ARFIMA-EWLLWNN model. Our methodologies integrate the advantages of the long-memory model, EW decomposition technique, artificial neural network structure, and backpropagation and particle swarm optimization learning algorithms. The experimental results of the optimized hybrid approach outperform some classic models by providing more accurate out-of-sample forecasts over longer horizons. The model proves to be the most appropriate Bitcoin forecasting technique. Moreover, the implemented method produces smaller prediction errors than other computing techniques.