Network Optimization Model Research Articles

Research on mechanical part recognition method based on improved mask R-CNN instance segmentation

Aiming at the problem of poor part recognition due to mutual occlusion between parts and the influence of different postures in the assembly scene, we propose an improved Mask R-CNN-based part recognition method for complex scenes. Firstly, the ResNet101 network is used to enhance the feature extraction capability of the network and improve the part recognition effect; secondly, the normalization layer of the backbone network is replaced to reduce the effect of batch size on the feature extraction of the model; lastly, the feature pyramid network structure is improved to enhance the transfer efficiency between the high and low layers of the network, and to enhance the capability of the feature capture; through the experiments on the homemade dataset, the average detection accuracy of this method is 4.7 % higher than that of the original Mask R-CNN. Through the experiments on the homemade dataset, it is found that compared with the original Mask R-CNN, the average detection accuracy of the method is improved by 4.7 %.The optimized network model proposed in this paper can improve the accuracy of part recognition, realize the accurate detection of parts in the complex environment such as stacking, occlusion and so on, and provide a solution for the recognition of parts in the complex environment.

Two-layer optimization model of distribution network line loss considering the uncertainty of new energy access

The integration of a distributed generator (DG) into the distribution network alters the topology structure and power flow distribution, subsequently causing changes in network loss. Moreover, existing distribution network optimization methods face high computational complexity, low efficiency, and susceptibility to local optima. This article proposes a scenario generation method using a generative adversarial network (GAN) to handle the uncertainty associated with DGs and constructs a two-layer optimization model for the distribution network. The upper layer model determines the installation location and capacity of distributed power and energy storage systems with the lowest economic cost. The lower layer model establishes an optimization model, including wind, solar, and storage, with active power network loss and voltage deviation as objective functions. Both layers are solved using the Improved Whale Optimization algorithm (IWOA). Then, the IEEE-33 node distribution system was taken as a simulation example to verify the effectiveness and superiority of the proposed model and algorithm.

Research on peanut pedigree analysis and variety identification methods based on deep features extraction and hierarchical clustering

Abstract In order to screen high-quality peanut pod varieties on food processing production lines and promote the sustainable development of the peanut as well as the expansion of its consumer market, this study improved the recognition ability of peanut pod varieties and the efficiency of deep feature extraction by optimizing the ResNet50 deep learning network model. Experimental results showed that the accuracy of the optimized network model reached 91.6%, which was 2.1% higher than the original ResNet50 model. Additionally, this study extracted the deep features of the appearance morphology of peanut pods, used the agglomerative clustering method to explore the genetic relationship of hybrid offspring varieties under the same line, and constructed a pedigree diagram containing 18 varieties. These research findings provide a crucial scientific foundation for the cultivation of high-quality peanut varieties. The selected high-quality peanuts not only enhance the added value of the peanut industry but also further expand the market potential of peanut by-products.

A Hybrid Distribution Network Model for Cost, Quality and Distribution Optimization in Perishable Goods Supply Chains

The entrenched role of syndicates and intermediaries in the perishable goods sector inflates prices through artificial scarcity and hoarding, creating significant affordability challenges. Addressing these issues is critical amid rising global demand for fresh produce, which is highly vulnerable to quality degradation due to Supply Chain (SC) inefficiencies and inadequate cold storage practices. Consequently, formulating an SC Distribution Network (SCDN) becomes imperative to optimize distribution planning, mitigate quality deterioration, and ensure the sustainability of the SC. This research proposes an advanced SCDN architecture by developing a mixed-integer linear programming (MILP) model tailored for multi-echelon scenarios. The model aims to minimize overall SC costs, reduce cold storage expenses, and preserve the freshness of perishable goods through an efficient and hybrid distribution channel. The proposed model integrates competing objectives by addressing a multi-criteria problem via the weighted sum method (WSM) and is executed using the GUROBI optimizer in Python. Two case studies centred on the distribution of Mango and Jack fruits in Bangladesh validate the model's practicality. The findings highlight the strategic importance of optimal distribution center placement and a dual supply strategy, with plants meeting 63% of mango and 53% of jackfruit demand, reducing reliance on intermediaries by advocating direct shipping to markets while bypassing cold storage. This study further highlights the model's robustness and offers critical managerial insights, facilitating informed decision-making in the complex landscape of perishable product supply chains.

A hierarchical overlay network optimisation model for enhancing data transmission performance in blockchain systems

A hierarchical overlay network optimisation model for enhancing data transmission performance in blockchain systems

A Comparative Exploration of BERT, RNN, and GRU for Sentiment Classification

Sentiment classification tasks are a large branch of current natural language processing problems. The purpose of this task lies in determining the sentiment that the text is trying to convey given a piece of text or sentence. This technique can be widely referenced in areas such as, monitoring market opinion, protecting social security, and developing ai customer service. Currently, the most advanced solutions to the sentiment classification problem are based on Bidirectional Encoder Representations from Transformers (BERT), in order to try to research a better solution, this study will start from the bottom, first find the optimal Recurrent Neural Network (RNN) model to pave the way for future improvements. The research method is to start from one layer and keep adjusting the parameters or RNN types until the best model is found. Through an experimental study, it was found that the two-layer bidirectional Long Short-Term Memory (LSTM) performed best on the sentiment classification problem with an accuracy of 93.21%. It proves that LSTM is better than Gated Recurrent Unit (GRU) and simple RNN in understanding long text, and in the future, more datasets can be collected from other platforms, not twitter, and then the model can be trained more complexly, which will help the model to be generalized to other domains or occasions.

Groundwater Nitrate Modeling in Tehran Metropolis Using Artificial Neural Network and Kriging Methods

This study examined the relationship between groundwater quality and land use in Tehran. For this purpose, the possible relationship between the types of land uses and the concentration of nitrate in groundwater parameters was modelled using a Multi-Layer Perceptron (MLP) artificial neural network in geographic information system (GIS). The optimal network model was selected based on the mean root mean square error (RMSE) and correlation coefficient. Interpolation through Kriging was also performed to compare its results with those of the predicted model derived from an artificial neural network. The results showed that the neural network has a high capability for predicting and modelling groundwater nitrate concentration compared to the Kriging method. The high accuracy (RMSE: 0.003) of the neural network makes it a useful tool in relevant management issues. Our results of network sensitivity analysis were similar to scientific findings regarding the factors influencing the formation of nitrate in groundwater. Model outputs in the form of maps, tables, and graphs allowed the study of the role of each variable and the extent of its impact on groundwater quality. Performing various simulations and modelling of groundwater pollution provides an effective benchmark towards optimizing the management, control, planning, and decision-making in urban areas and can lead to economic and environmental savings.

Groundwater Nitrate Modeling in Tehran Metropolis Using Artificial Neural Network and Kriging Methods

This study examined the relationship between groundwater quality and land use in Tehran. For this purpose, the possible relationship between the types of land uses and the concentration of nitrate in groundwater parameters was modelled using a Multi-Layer Perceptron (MLP) artificial neural network in geographic information system (GIS). The optimal network model was selected based on the mean root mean square error (RMSE) and correlation coefficient. Interpolation through Kriging was also performed to compare its results with those of the predicted model derived from an artificial neural network. The results showed that the neural network has a high capability for predicting and modelling groundwater nitrate concentration compared to the Kriging method. The high accuracy (RMSE: 0.003) of the neural network makes it a useful tool in relevant management issues. Our results of network sensitivity analysis were similar to scientific findings regarding the factors influencing the formation of nitrate in groundwater. Model outputs in the form of maps, tables, and graphs allowed the study of the role of each variable and the extent of its impact on groundwater quality. Performing various simulations and modelling of groundwater pollution provides an effective benchmark towards optimizing the management, control, planning, and decision-making in urban areas and can lead to economic and environmental savings.

DON: Deep Optimized Network model based on Coot and Convoluted Recurrent learning algorithms for healthcare monitoring in IoMT systems

The major challenges faced in the modern era involve fulfilling urgent needs for multi-access health-tracking systems and reliable identification of diseases. Recent advancements in IoMT and technological innovations are shaping the adoption of smart healthcare systems widely across the world. A sophisticated, round-the-clock health monitoring system is required for the efficient tracking of patients, together with timely medical interventions. State-of-the-art computing and cloud infrastructures shall be demanded from smart medical facilities. This work presents the development of a Deep Optimized Network model: IoMT-enabled intelligent, automated edge computing environment for healthcare monitoring in disease diagnosis. In this regard, we have utilized the technique of feature selection, called Coot Optimized Feature Selection, for choosing only the relevant features from preprocessed medical data so that the performance of the classifier improves both at the time of training and at testing. Further, we propose a novel deep learning-based algorithm called the Convoluted Recurrent Attention Network, CRAN, which can identify and classify various diseases related to genetic disorder, chronic disease, or heart-related disorder while maintaining low time complexity with high efficiency. In this respect, the hyper-parameters of the CRAN model are fine-tuned using the Cray Fish Optimization technique, allowing optimal classification learning. Extensive performance evaluations using the widely recognized open-source medical datasets validate the effectiveness of the proposed DON model. The results identify the outcomes of the model with high accuracy in the classification of diseases, establishing it as a reliable solution for effective health monitoring. From these findings, one may infer that the integration of IoMT with advanced computational techniques would definitely enhance the healthcare delivery systems. With the DON model, high accuracy in disease identification and efficient monitoring lead to better patient outcomes by ensuring streamlined healthcare processes.

TGPO-WRHNN: Two-stage Grad-CAM-guided PMRS Optimization and weighted-residual hypergraph neural network for pneumonia detection

Recent studies based on chest X-ray images have shown that pneumonia can be effectively detected using deep convolutional neural network methods. However, these methods tend to introduce additional noise and extract only local feature information, making it difficult to express the relationship between data objects. This study proposes a Two-stage Grad-CAM-guided pre-trained model and removal scheme (PMRS) Optimization and weighted-residual hypergraph neural network model (TGPO-WRHNN). First, our model extracts high-dimensional features using the TGPO module to capture both global and local information from an image. Second, we propose a new distance-based hypergraph construction method (DBHC) to amplify the difference between distances and better distinguish the relation between nearby and distant neighbors. Finally, we introduce a weighted-residual hypergraph convolution module (WRHC) to ensure the model maintains excellent performance, even at deeper levels. Our model was tested on a dataset of chest X-ray images of pediatric patients aged 1 to 5 years at the Guangzhou Women and Children’s Medical Centre by 10-fold cross-validation. The results showed that the method achieved a maximum accuracy of 98.97%, precision of 98.86%, recall of 98.43%, F1 score of 98.64%, and AUC of 99.78%. Compared to other existing models, our model demonstrated improvements of 0.87%, 0.86%, 0.16%, and 0.38% in terms of accuracy, precision, F1 score, and AUC, respectively.

Artificial intelligence as an auxiliary tool in pediatric otitis media diagnosis

ObjectivesIn order to promote the use of AI technology as the auxiliary tool in pediatric otitis media diagnosis, we use the convolutional neural networks and deep learning for image classification and disease diagnosis. We also designed a Pediatric Otitis Media Classifier to analyze and classify the images for physicians. MethodsA pediatric otitis media classifier was designed for junior physicians (doctors who have been engaged in clinical practice for a short time) as an auxiliary diagnostic tool. To design this classifier for children with otitis media, we used a large number of images of acute otitis media (AOM), secretory otitis media (OME), and normal otoscope images to obtain the optimal convolutional neural network model. ResultsThe average recognition accuracies of the ZFNet and the TSL16 for classification were 97.87 % and 97.62 %, far exceeding the accuracy of human diagnosis. The results of using the Pediatric Otitis Media Classifier show that we can use the classifier to correctly identify the image types of child middle ear infections. ConclusionsWe developed the Pediatric Otitis Media Classifier for the successful automated classification of AOM and OME in children using otoscopic images. In contrast to the traditional diagnosis of pediatric otitis media, which relies heavily on the experience of doctors, the diagnostic accuracy of even experienced physicians is only approximately 80 %. With AI technology, we can improve the accuracy rate to over 98 %, which can effectively assist doctors in auxiliary diagnosis. It also reduces delayed treatment, antibiotic misuse, and unnecessary surgery caused by misdiagnosis.

Multi-charging Station access distribution network grid planning and optimization method based on MRFO algorithm

Abstract The traditional multi-charging station integration into the distribution network planning and optimization model is a regional optimization process with low overall efficiency, increasing the total optimization cost. Therefore, a multi-charging station access distribution network based on the MRFO (Manta Ray Foraging Optimization) algorithm is proposed. The MRFO calculation method was adopted to improve overall efficiency, and the design of the MRFO calculation multi-charging station access distribution network planning optimization model was completed. Optimization processing and multi-objective validation are used to achieve grid optimization. The test results show that the MRFO calculation and distribution network planning optimization method designed in this study ultimately achieve a relatively low total optimization cost, better optimization effect, and practical application value.

Enhancing 3D geological and geotechnical engineering model of Bangkok subsoil using optimal deep neural network models

Enhancing 3D geological and geotechnical engineering model of Bangkok subsoil using optimal deep neural network models

Revisiting the traffic flow observability problem: A matrix-based model for traffic networks with or without centroid nodes

This study introduces a graph theory-based model that addresses the link flow observability problem in traffic networks by optimizing passive sensor deployment. The model aims to determine the minimal number of sensors and their optimal placement. It constructs a virtual network and uses isomorphic graph theory to map between the original and virtual networks, ensuring consistency in nodes, links, and link directions. Two formulas are proposed to calculate the minimum number of observable links required across different networks, factoring in links, ordinary nodes, centroid nodes, and added links. Key concepts such as chords, cut sets, and loops, along with their matrices, are analyzed. A matrix-based framework is developed to consider flow conservation conditions. Results show that solving the full link flow observability problem using node flow conservation equations yields a fixed number of sensors with non-unique deployment schemes, Additionally, a resource-constrained sensor network optimization (RSNO) model is presented, employing null space projection (NSP) as an objective function to quantify the impact of budget constraints particularly under the condition if all the link flows cannot be observed. Numerical examples demonstrate the RSNO model's applications.

Offshore carbon storage from power plants based on real option and multi‐period source‐sink matching: A case study in the eastern coastal China

Carbon capture utilization and storage (CCUS) emerges as a pivotal strategy for CO2 reduction in the power sector, particularly focusing on the overlooked domain of offshore storage along China's east coast. In spite of the potential high costs, irreversible investments, and lengthy development, offshore storage can still be prospective. Considering autonomous decision-making among emission sources, this study pioneers a CO2 offshore storage investment decision model tailored for coal-fired and gas-fired power plants. Innovating an offshore storage source-sink matching model with a real options model and introducing a pipeline network optimization model allows a realistic source-sink matching strategy to be explored under optimal investment timing. According to the results, among 154 large stationary emission sources in Zhejiang Province, offshore storage could reduce CO2 emissions by 4.59 Gt, utilizing the Qiantang, Minjiang, and Fuzhou depressions. It is economically feasible to implement offshore storage with a whole-process unit cost of 368.8 CNY/tCO2, mainly dominated by capture costs. A hybrid carbon tax-subsidy policy promotes carbon reduction and economic benefits, offering a more effective incentive for emission sources to invest in offshore storage than a single policy. At a hybrid policy price of 250 CNY/tCO2, all 27 selected emission sources are projected to invest in offshore storage by 2048, with a preference for the Qiantang depression as the storage site. Practically, this study provides important technical support and guidance for the large-scale deployment of offshore storage.

Designing a resilient supply chain network: A multi-objective data-driven distributionally robust optimization method

Uncertainty of supply chain disruption poses a significant challenge to decision-making in many real-life problems. In this paper, a new multi-objective data-driven distributionally robust optimization (MDDRO) model for the resilient supply chain network (RSCN) design problem under disruption scenario is developed, which includes minimizing the total cost, carbon emissions, and delivery time. In the context of supply chain disruption, it is important self-evidently that products can be supplied normally and the practical demand can be met. In handling the partial probability distribution information of the considered uncertain demand, this paper uses a data-driven Wasserstein-Moment ambiguity set (WMAS), which incorporate the Wasserstein metric and Moment information, and a robust counterpart to transform the developed model into a tractable approximation form. The finite-sample performance guarantee of the optimal solution of MDDRO model with Wasserstein-Moment ambiguous chance constraint is given. An accelerated Branch and cut algorithm (BCA) is constructed to solve the MDDRO model. Finally, through the investigation of a real-life case and sensitivity analysis of key parameters, some managerial insights are put forward.

Real-time robust liver and gallbladder segmentation during laparoscopic cholecystectomy using convolutional neural networks: an analysis

Aim: Images in different laparoscopic cholecystectomy datasets are acquired using various camera models, parameters, and settings, with the annotation methods varying by institution. These factors result in inconsistent inference performance of the network model. This study aims to identify the optimal network model architecture for liver and gallbladder segmentation from several options. Then, the performance and robustness of the optimal network model are evaluated using an independent dataset that is not included in the training. Methods: The public dataset, CholecSeg8k, was utilized as the input for the network model training, validation, and testing. A local private dataset from KPJ Damansara Hospital, Selangor, Malaysia, was used for testing purposes only. For the implementation of liver and gallbladder segmentation, segmentation models, a public Python library was employed. Results: Among the experiments, highly accurate liver and gallbladder segmentation results were achieved using the feature pyramid network (FPN) architecture as the network model, with the Inception-ResNet-v2 architecture as the network backbone. The best-trained network model resulted in a loss of 0.070955, a mean intersection over union (IoU) score of 0.95896, and a mean F1-score of 0.9773 on the test set. However, visualized results for the private dataset contained considerable false-negative areas. Conclusion: The proposed automated technique has the potential to serve as an alternative to the conventional indocyanine green injection along with near-infrared fluorescence imaging (ICG-NIRF)-based method for liver and gallbladder segmentation during laparoscopic cholecystectomy. Future work will focus on enhancing the results of the private dataset. Additionally, a surgeon-assistant robotic arm that will use the liver and gallbladder segmentation results for camera steering will be analyzed.

Fasteners quantitative detection and lightweight deployment based on improved YOLOv8.

Currently, research on on-board real-time quantitative detection of rail fasteners is few. Therefore, this paper proposes and validates an improved YOLOv8 based method for quantitative detection of rail fasteners, leveraging the capabilities of edge miniaturized artificial intelligence (AI) computing devices. First, the lightweight MobileNetV3 is employed as the backbone network for our model to increase detection speed, and the SA attention mechanism is integrated at the end of the backbone network to enhance the feature of the fasteners. Then the deformable convolution is introduced to reconstruct the bottleneck structure of the neck network, which can segment fasteners without compromising accuracy. Subsequently, the optimized network model is utilized on a Jetson AGX Xavier edge AI computing device by the TensorRT acceleration method. Segmentation results are then extracted at the pixel level for quantitative analysis of fastener breakage degree and deflection angle, so as to correct the detection results. Experimental results show that the size of the improved lightweight network volume is reduced by 28% compared to the original YOLOv8 model, and the frame rate on the edge AI computing device is lifted by 71.87%, i.e., 55 f/s. Furthermore, the model is refined based on quantitative analysis results, resulting in an mAP0.5 of 97.0%, and real-time quantitative detection of rail fasteners is realized.

SADO-Net: A spatial adaptive dart optimized network model for an automated brain tumor diagnosis using MRIs

Early detection of brain tumors is essential, and a biopsy is required to determine the type of tumors in the brain and is only possible after extensive brain surgery. Brain tumors can be identified and classified by clinicians with the aid of computational intelligence algorithms. Here, we developed an novel and intelligent automated system, known as, Spatial Adaptive Dart Optimized Network (SADO-Net) for the diagnosis of brain tumor using MRIs. This will allow medical professionals to identify tumors in their early stages with a high degree of accuracy. Before classifying the diseases, the preprocessed brain MRIs are segmented using the Spatial Pattern based Image Segmentation (SPISeg) technique. The type of brain tumor is then promptly and reliably identified using the Weight Optimized Deep Network (WODNet) Classification model. The adoption of the Darts Game based Optimization (DGO) method for feature reduction expedites the classification process. This work uses a range of metrics and popular public datasets such as BRATS 2018, BRATS 2019, BRATS 2020 and Figshare to compare and validate the performance of the proposed SADO-Net model in tumor identification. Based on the results, the SADO-Net model exhibits good performance, with an average accuracy of 99.2 % and a loss rate of 0.5 %.

Assessment of machine learning models trained by molecular dynamics simulations results for inferring ethanol adsorption on an aluminium surface

Molecular dynamics (MD) simulations can reduce our need for experimental tests and provide detailed insight into the chemical reactions and binding kinetics. There are two challenges while dealing with MD simulations: one is the time and length scale limitations, and the latter is efficiently processing the massive amount of data resulting from the MD simulations and generating the proper reaction rates. In this work, we evaluated the use of regression machine learning (ML) methods to solve these two challenges by developing a framework for ethanol adsorption on an Aluminium (Al) slab. This framework comprises three main stages: first, an all-atom molecular dynamics model; second, ML regression models; and third, validation and testing. In stage one, the adsorption of ethanol molecules on the Al surface for various temperatures, velocities and concentrations is simulated using the large-scale atomic/molecular massively parallel simulator (LAMMPS) and ReaxFF. The outcome of stage one is utilised for training, testing, and validating the predictive models in stages two and three. We developed and evaluated 28 different ML models for predicting the number of adsorbed molecules over time, including linear regression, support vector machine (SVM), decision trees, ensemble, Gaussian process regression (GPR), neural network (NN) and Bayesian hyper-parameter optimisation models. Based on the results, the Bayesian-based GPR showed the highest accuracy and the lowest training time. The developed model can predict the number of adsorbed molecules for new cases within seconds, while MD simulations take a few weeks. This adsorption rate can then be used in macroscale simulations to tackle the time and length scale limitations. The proposed numerical framework has the potential to be generalised and, therefore, contribute to future low-cost binding reaction estimations, providing a valuable tool for industry and experimentalists.