Algorithmic Framework Research Articles

Glass Defect Detection with Improved Data Augmentation under Total Reflection Lighting

To address the technical challenge of identifying tiny defects, especially dust and point defects, on mobile phone flat glass, an automatic optical inspection system is established. The system investigates algorithms including imaging principles, target detection models, data augmentation, foreground segmentation, and image fusion. The system builds an automatic optical inspection platform to collect glass defect samples. It illuminates the glass samples with a combined total reflection–grazing light source, collects the defect sample data, segments the background and defects of the collected data, generates the defect mask, and extracts the complete defects of the cell phone flat glass. The system then seamlessly integrates the extracted defects with a flawless background using Poisson editing and outputs the location information of the defects and the label output to automatically generate the dataset. The deep learning network YOLOv5 works as the core algorithm framework, into which the Constructive Block Attention Module and the small target detection layer are specifically added to enhance the capability of the model to detect small defects. According to the experimental results, the combined lighting effectively improves the precision of detecting dust and bright spots. Additionally, with the adoption of novel data augmentation techniques, the enhanced YOLOv5 model is capable of effectively addressing the challenges posed by inefficient sample data and non-uniform distribution, thus mitigating network generalization issues. Furthermore, this data augmentation approach facilitates the rapid adaptation of the same detection tasks to diverse environmental scenarios, enabling the expedited and efficient deployment of the model across various industrial settings. The mean average precision (MAP) of the optimal model in the validation set reached 98.36%, 2.62% higher than that of the original YOLOv5. In addition, its false acceptance rate (FAR) is 1.27%, its false rejection rate (FRR) was 2.47%, its detection speed was 64 fps, and its correct detection rate in the validation set was 98.75%, which meets the current industrial detection requirements by and large. In this way, this paper achieved the automated inspection of mobile phone flat glass with high robustness, high precision, and a low false acceptance rate and false rejection rate, significantly reducing material losses in the factories and the likelihood of error occurrence in follow-on products. This method can be applied to the multi-scale and multi-type detection of glass defects.

Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review

Change detection is an essential and widely utilized task in remote sensing that aims to detect and analyze changes occurring in the same geographical area over time, which has broad applications in urban development, agricultural surveys, and land cover monitoring. Detecting changes in remote sensing images is a complex challenge due to various factors, including variations in image quality, noise, registration errors, illumination changes, complex landscapes, and spatial heterogeneity. In recent years, deep learning has emerged as a powerful tool for feature extraction and addressing these challenges. Its versatility has resulted in its widespread adoption for numerous image-processing tasks. This paper presents a comprehensive survey of significant advancements in change detection for remote sensing images over the past decade. We first introduce some preliminary knowledge for the change detection task, such as problem definition, datasets, evaluation metrics, and transformer basics, as well as provide a detailed taxonomy of existing algorithms from three different perspectives: algorithm granularity, supervision modes, and frameworks in the Methodology section. This survey enables readers to gain systematic knowledge of change detection tasks from various angles. We then summarize the state-of-the-art performance on several dominant change detection datasets, providing insights into the strengths and limitations of existing algorithms. Based on our survey, some future research directions for change detection in remote sensing are well identified. This survey paper sheds some light the topic for the community and will inspire further research efforts in the change detection task.

Multi-Scale Attention and Dilated Convolutional Neural Network-Based 3D Scene Reconstruction for Moving Objects

Three-dimensional (3D) scene reconstruction for moving objects remains a challenging research topic. It is crucial to effectively capture feature representations from dynamic and complex scenarios. Consequently, this work introduces the integration of multi-scale attention and dilated convolution to create an enhanced deep-learning structure for this purpose. Therefore, this paper proposes a 3D reconstruction method for moving objects based on multi-scale attention and a dilated convolutional neural network (CNN). Specifically, a multi-scale attention algorithm framework that incorporates dilated CNNs is designed to extract multi-scale features of moving targets. The dilated CNN is incorporated to enhance the model’s perception ability and receptive field while maintaining a lightweight structure. This integrated design aims to achieve automatic learning targeted at features and scene information at different scales. By increasing the effective range of information perception and further enhancing the quality of reconstruction results, a coordinate system is established for 3D scene reconstruction of moving targets. Finally, a comparative analysis of subjective vision, visualization, and reconstruction algorithms is conducted using real-world cases. The experimental results demonstrate that the proposed method exhibits significant advantages in the 3D scene reconstruction task of moving targets compared to traditional methods.

Optimal capacity and multi-stable flexible operation strategy of green ammonia systems: Adapting to fluctuations in renewable energy

The potential of power-to-ammonia is increasingly recognized as a large-scale renewable electrical energy storage technology in the energy-transition landscape. Unlike conventional, continuously operating Haber-Bosch production processes, power-to-ammonia processes face operational challenges stemming from fluctuations in renewable power supply. Systematic strategies that can adapt to these fluctuations are required to improve the operational flexibility and stability of power-to-ammonia processes for industrial applications. This study proposes a multi-stable flexible ammonia operation strategy, which is practical and feasible in engineering. To maximize net profit, a design scheduling coordination optimization model is established and solved using a two-stage algorithmic framework of particle swarm and mixed integer linear programming. Additionally, three flexible scenarios are designed for the simulation analysis of a grid-connected green ammonia system. Compared with the traditional constant inflexible scenario, the multi-stable flexible scenario increases annual net profit by 5.05 M$ and reduces carbon emission intensity by 1.61 kg CO2/kgNH3. Furthermore, compared with the continuous flexible scenario, the volatility of the ammonia production load is reduced by 79.89 %. The multi-stable flexible operation strategy balances the green ammonia system’s economic, safety, and low-carbon attributes. Sensitivity analysis reveals that wind and photovoltaic complementary power generation reduces green ammonia costs and carbon emissions. When the selling price of ammonia exceeds 550 $/t, ammonia production and sales should be prioritized, but at lower ammonia prices, selling electricity to the grid to optimize economic efficiency is advised. This study provides novel insights into the flexible operation of the power-to-ammonia process and is expected to offer guidance for constructing and operating green ammonia systems.

Federated deep reinforcement learning for task offloading and resource allocation in mobile edge computing-assisted vehicular networks

Mobile edge computing (MEC) enables computation intensive applications in the Internet of Vehicles (IoV) to no longer be limited by device resources. However, the lack of an effective task scheduling strategy will seriously affect users’ quality of experience (QoE). In this paper, a task type-based task offloading and resource allocation strategy is proposed to reduce delay and energy consumption during task execution. First, we establish communication, computing, and system cost models based on task offloading schemes, and model the joint optimization problem of task offloading and resource allocation as a Markov decision process. The utility function is obtained based on the task completion rate and the system cost. Second, an algorithm framework based on multi-agent deep deterministic policy gradient (MADDPG) is designed to solve the difficulty that traditional single-agent reinforcement learning algorithms are difficult to converge in a dynamic environment. In distributed scenarios, the proposed framework can also reduce system costs while handling more tasks. Finally, federated learning is introduced in the training process to reduce the impact of non-IID data while protecting privacy. Simulation results show that the proposed algorithm can effectively improve system processing efficiency and reduce device energy consumption compared to the popular reinforcement learning algorithms.

Big Data Privacy Protection and Security Provisions of the Healthcare SecPri-BGMPOP Method in a Cloud Environment

One of the industries with the fastest rate of growth is healthcare, and this industry’s enormous amount of data requires extensive cloud storage. The cloud may offer some protection, but there is no assurance that data owners can rely on it for refuge and privacy amenities. Therefore, it is essential to offer security and privacy protection. However, maintaining privacy and security in an untrusted green cloud environment is difficult, so the data owner should have complete data control. A new work, SecPri-BGMPOP (Security and Privacy of BoostGraph Convolutional Network-Pinpointing-Optimization Performance), is suggested that can offer a solution that involves several different steps in order to handle the numerous problems relating to security and protecting privacy. The Boost Graph Convolutional Network Clustering (BGCNC) algorithm, which reduces computational complexity in terms of time and memory measurements, was first applied to the input dataset to begin the clustering process. Second, it was enlarged by employing a piece of the magnifying bit string to generate a safe key; pinpointing-based encryption avoids amplifying leakage even if a rival or attacker decrypts the key or asymmetric encryption. Finally, to determine the accuracy of the method, an optimal key was created using a meta-heuristic algorithmic framework called Hybrid Fragment Horde Bland Lobo Optimisation (HFHBLO). Our proposed method is currently kept in a cloud environment, allowing analytics users to utilise it without risking their privacy or security.

A penalty-free hybrid algorithm framework based on feasible stream matching principle for large-scale heat exchanger networks synthesis

In this work, a penalty-free hybrid stochastic-deterministic algorithm framework is proposed for large-scale heat exchanger networks (HENs) synthesis (HENS), formulated as a computationally-hard mixed-integer nonlinear programming (MINLP) problem. In the outer level, an improved genetic algorithm (GA) is developed to optimize process stream matches represented by integer variables whose values are generated by a unique heat exchanger vector. Unlike previous researches, the improved GA does not rely on any penalty terms, because we propose a feasible stream matching principle to exclude all infeasible process stream matches and only feasible matches are considered in optimization process. In the inner level, a reduced-size MINLP model is solved using deterministic methods to minimize total annualized costs (TACs), which are then used to evaluate the fitness of candidate HENs. Through this way, the proposed framework combines deterministic and stochastic methods to enhance optimization efficiency and global search capability. Illustrative tests on six benchmark cases demonstrate that the framework can efficiently achieve lower-cost solutions compared to deterministic, stochastic, or hybrid methods. The results show a decrease in TAC for all six cases and a reduction in solution time ranging from 11.1% to 97.2%. Importantly, the proposed framework can be extended to solve MINLP problems in other process networks.

Modeling, prediction and analysis of natural gas consumption in China using a novel dynamic nonlinear multivariable grey delay model

Accurately predicting natural gas consumption is essential for developing a clean, low-carbon, safe, and efficient energy system. Therefore, this paper integrates the idea of the extended logistic model into multivariable grey prediction theory. Considering the delay effect and nonlinear characteristics of the system, a novel dynamic nonlinear multivariate grey delay prediction model is constructed. Meanwhile, the algorithmic framework for solving the parameters of the new model is provided to identify and optimize the parameters of the time-delay effect of the model. The genetic algorithm was identified as the best matching optimization algorithm for the new model. Furthermore, the new model is applied to fitting and forecasting China's natural gas consumption, and the validity of the model is fully verified. Compared with other forecasting models, the new model has a lower average relative error in the fitting and forecasting stage, and, in particular, achieves a better forecasting effect with the lowest MAPEpre value (0.001 % for one-step ahead, 0.005 % for two-step ahead, and 0.746 % for three-step ahead). Moreover, the model is employed to forecast China's natural gas consumption for the next five years, providing a robust foundation for government policies related to the supply of natural gas.

Development and evaluation of an algorithm for peripheral venous catheter placement (ALCOV): protocol for a quasi-experimental study

IntroductionMultiple punctures during peripheral venous catheter (PVC) placement increase the risk of complications. Scoring for adult difficult intravenous access (A-DIVA Scale) exists but has never been assessed in the framework...

A multi-population multi-stage adaptive weighted large-scale multi-objective optimization algorithm framework

Weighted optimization framework (WOF) achieves variable dimensionality reduction by grouping variables and optimizing weights, playing an important role in large-scale multi-objective optimization problems. However, because of possible problems such as duplicate weight vectors in the selection process and loss of population diversity, the algorithm is susceptible to local optimization. Therefore, this paper develops an algorithm framework called multi-population multi-stage adaptive weighted optimization (MPSOF) to improve the performance of WOF in two aspects. First, the method of using multi-population is employed to address the issue of insufficient algorithmic diversity, while simultaneously reducing the likelihood of converging towards local optima. Secondly, a processing stage is incorporated into MPSOF, where a certain number of individuals are adaptively selected for updating based on the weight information and evolutionary status of different subpopulations, targeting different types of weights. This approach alleviates the impact of repetitive weights on the diversity of newly generated individuals, avoids the drawback of easily converging to local optima when using a single type of weight for updating, and effectively balances the diversity and convergence of subpopulations. Experiments of three types designed on several typical function sets demonstrate that MPSOF exceeds the comparison algorithms in the three metrics for Inverse Generation Distance, Hypervolume and Spacing.

An algorithmic framework for synthetic cost-aware decision making in molecular design.

Small molecules exhibiting desirable property profiles are often discovered through an iterative process of designing, synthesizing and testing sets of molecules. The selection of molecules to synthesize from all possible candidates is a complex decision-making process that typically relies on expert chemist intuition. Here we propose a quantitative decision-making framework, SPARROW, that prioritizes molecules for evaluation by balancing expected information gain and synthetic cost. SPARROW integrates molecular design, property prediction and retrosynthetic planning to balance the utility of testing a molecule with the cost of batch synthesis. We demonstrate, through three case studies, that the developed algorithm captures the non-additive costs inherent to batch synthesis, leverages common reaction steps and intermediates, and scales to hundreds of molecules.

Ensemble-based multimodal medical imaging fusion for tumor segmentation

The use of multimodal medical imaging is on the rise, both in academic and clinical settings. There was a meteoric growth in the use of multimodal imaging analysis (MIA) with the addition of ensemble learning techniques, which had particular advantages in the medical field. We provide an algorithmic framework that allows supervised MIA and Cross-Modality Fusing at the preprocessing phase algorithms for classification and decision-making levels, drawing inspiration from the current triumphs of deep learning approaches in medical imaging. We presented a method for picture segmentation that makes use of sophisticated convolutional neural networks to identify lesions produced by tumors in soft tissues. To do this, MRI tomography and PET scans are combined to provide multi-modal images. Networks trained with multimodal images outperform their single-modal counterparts. When it relates to tumor segmentation, fusing photos throughout the neural network (i.e., within the convolutional layer or totally connected layers) yields better results than photographs that merge the network’s output. The proposed approach employs four pre-trained models, specifically VGG 19, ResNet 50,SqueezeNet, as well as DenseNet 121. Using a dataset of ISL images, the pre-trained models are fine-tuned. Subsequently, the ensemble learning technique is employed to combine the predictions generated by the three models. Here, ensemble is based on a weighted voting method. Impressive results were obtained with the proposed ensemble method: 98.1% accuracy, 97.5% F1 score, and 90.8% Kappa score. The ensemble method outperformed individual models and existing approaches for multimodal medical fusion and classification, with a Jaccard score of 93.8% and a recall of 98.2% demonstrate its effectiveness for multimodal medical fusion and classification.

A Review of Deep Learning-Based LiDAR and Camera Extrinsic Calibration

Extrinsic parameter calibration is the foundation and prerequisite for LiDAR and camera data fusion of the autonomous system. This technology is widely used in fields such as autonomous driving, mobile robots, intelligent surveillance, and visual measurement. The learning-based method is one of the targetless calibrating methods in LiDAR and camera calibration. Due to its advantages of fast speed, high accuracy, and robustness under complex conditions, it has gradually been applied in practice from a simple theoretical model in just a few years, becoming an indispensable and important method. This paper systematically summarizes the research and development of this type of method in recent years. According to the principle of calibration parameter estimation, learning-based calibration algorithms are divided into two categories: accurate calibrating estimation and relative calibrating prediction. The evolution routes and algorithm frameworks of these two types of algorithms are elaborated, and the methods used in the algorithms’ steps are summarized. The algorithm mechanism, advantages, limitations, and applicable scenarios are discussed. Finally, we make a summary, pointing out existing research issues and trends for future development.

Review of Two-timescale Stochastic Approximation Algorithms

Artificial Intelligence has gradually become an important force to drive human beings into the intelligent era, and machine learning has made great contributions to the rise and development of Artificial Intelligence. Stochastic approximation (SA) is a com-monly used optimization algorithm in machine learning, and with the complexity of practical problem scenarios, two-timescale SA have received extensive attention and research. In this paper, the basic idea and development process of SA are introduced firstly, followed by the description of several algorithmic frameworks for linear and nonlinear SA, and the specific applications of two-timescale SA in the fields of opti-mization and reinforcement learning are also introduced. Finally, the two-timescale SA is summarized and outlooked.

An adaptive strategy based multi-population multi-objective optimization algorithm

An algorithm is sensitive to parameters; different parameter settings for solving optimization problems can thus have a serious impact on algorithm performance. This leads to an inability to determine the optimal set of parameters for the algorithm to solve the problem at hand. In this study, we propose an adaptive strategy with a multi-population multi-objective algorithm (A-MPMO) framework to select the appropriate set of genetic settings according to the problem to be solved and eliminate the sensitivity of the algorithm to the parameters. Multi-population are often combined with Evolutionary Algorithms (EAs) as an effective strategy to maintain population diversity. First, we divided the population generated by the algorithm into multiple subpopulations to expand the search range and updated them iteratively using operators with different genetic parameters. Second, based on multi-population, subpopulations compete for limited computational resources, implying that the size of each subpopulation adaptively adjusts according to the degree of its contribution to problem solving. Finally, a set of subpopulations that are best suited to solve the problem is selected to improve the adaptability to different problems. For DTLZ, ZDT, and UF, compared to the other algorithms, A-MPMO was experimentally shown to produce better performance.

Poster Design Research Based on Deep Learning Automatic Image Generation Algorithm

Although this research has made significant progress in image generation models, they still face issues such as insufficient diversity of generated images, poor quality of high-resolution images, and the need for a large amount of training data for model optimization. This paper studies poster design based on deep learning automatic image generation algorithm, using a recursive supervised image generation algorithm framework of generative adversarial networks for multi-view image generation and super-resolution generation tasks of small sample digital poster images. Various improvements have been proposed to enhance the performance of the GAN network model for poster design image generation tasks. Based on experimental research, this paper’s model uses generative adversarial networks to distinguish randomly cropped low resolution and high-resolution poster blocks, ensuring that high-resolution posters maintain their original resolution canvas texture and brush strokes, effectively improving the automatic generation effect of poster images. The evaluation results show that the quantitative evaluation of the proposed algorithm model in knowledge management is distributed in a reasonable range, which indicates that the proposed algorithm model has good performance in knowledge management. The poster design model based on deep learning automatic image generation algorithm proposed in this paper has certain effects. In subsequent practice, the automatic image generation algorithm can be combined with practical needs to improve the efficiency and design effect of poster design.

Assessing vessel transportation delays affected by tropical cyclones using AIS data and a bayesian network: A case study of veronica in northwestern Australia

Tropical cyclones frequently disrupt maritime transportation systems, impacting the normal operation of vessels and causing transportation delays. Analyzing the occurrence and degree of vessel transportation delays under disaster conditions is one of the critical aspects of maritime transportation management. This article, based on Automatic Identification System (AIS) data, examined the real behavioral trajectories of vessels and delay characteristics during tropical cyclones. Taking the example of Tropical Cyclone Veronica, which occurred in the waters off northwestern Australia in 2019, we conducted a comprehensive analysis. This involved numerical simulations of the entire disaster process and the cleaning and matching of trajectory data for all affected vessels in the area. We delved deeply into the relationship between vessel behavior characteristics and tropical cyclones, identified factors contributing to delays, and, based on our findings, constructed a Bayesian network inference model for vessel transportation delays under disaster conditions. This model uses information such as tropical cyclone intensity, vessel basic attributes, behavior choices, and port disaster avoidance measures as its primary nodes. The research results indicate that vessel rerouting, vessel loss of control, and waiting for port entry are the three major sources of vessel delays during disasters. Key influencing factors contributing to these consequences include port closure measures, the duration of vessels being adversely affected by strong winds, vessel tendencies toward loss of control, and risk preferences. To control the extent of vessel delays more effectively, it is crucial to prioritize these sensitive factors and strengthen monitoring and management efforts. This model is driven by real data, providing an objective reflection of real-world scenarios, and its effectiveness has been validated through sensitivity analysis. The research perspective and algorithmic framework presented in this paper offer a novel paradigm and fresh perspective for the study of maritime transportation disasters. The research findings have significant implications for bolstering the resilience of maritime transportation networks, enhancing our comprehension and anticipation of delays, and ensuring the continuity, security, and efficiency of the global supply chain for goods.

DREAMER: a computational framework to evaluate readiness of datasets for machine learning

BackgroundMachine learning (ML) has emerged as the predominant computational paradigm for analyzing large-scale datasets across diverse domains. The assessment of dataset quality stands as a pivotal precursor to the successful deployment of ML models. In this study, we introduce DREAMER (Data REAdiness for MachinE learning Research), an algorithmic framework leveraging supervised and unsupervised machine learning techniques to autonomously evaluate the suitability of tabular datasets for ML model development. DREAMER is openly accessible as a tool on GitHub and Docker, facilitating its adoption and further refinement within the research community..ResultsThe proposed model in this study was applied to three distinct tabular datasets, resulting in notable enhancements in their quality with respect to readiness for ML tasks, as assessed through established data quality metrics. Our findings demonstrate the efficacy of the framework in substantially augmenting the original dataset quality, achieved through the elimination of extraneous features and rows. This refinement yielded improved accuracy across both supervised and unsupervised learning methodologies.ConclusionOur software presents an automated framework for data readiness, aimed at enhancing the integrity of raw datasets to facilitate robust utilization within ML pipelines. Through our proposed framework, we streamline the original dataset, resulting in enhanced accuracy and efficiency within the associated ML algorithms.

Multivariate iterative nonlinear chirp mode decomposition: principles and applications

Abstract The rotor-bearing system (RBS) of a hydroelectric unit includes multiple components such as the rotor, rotor shaft, coupling, turbine, and main shaft. There is a strong coupling relationship between the vibration signals of multiple bearing sections. At the same time, the vibration signal of the RBS contains rich frequency components, which can effectively reflect the operating state of the shaft system of the unit. Therefore, synchronous signal analysis across multiple rotor bearing sections is required to completely grasp the operating status of the unit. In this study, the Multivariate Iterative Nonlinear Chirp Mode Decomposition (MINCMD) is proposed to analyze signals on multiple sections simultaneously. MINCMD follows the step-by-step extraction idea of Adaptive Multivariate Chirp Mode Decomposition (AMCMD), but it adopts a new algorithm framework by modifying the objective function. Furthermore, AMCMD does not converge well without a good initial instantaneous frequency (IF). Therefore, a method based on parameterized demodulation (PD) is introduced in MINCMD to solve the multi-channel frequency initialization problem. The effectiveness of the proposed algorithm is verified through a simulation test and real data from hydroelectric units.

ИСПОЛЬЗОВАНИЕ ЦИФРОВЫХ ТЕХНОЛОГИЙ ПРИ РЕАБИЛИТАЦИИ ПАЦИЕНТОВ С ПЕРВИЧНОЙ АДЕНТИЕЙ

Abstract. Introduction. Number of patients with hypodontia has increased at orthodontic appointments. According to different authors, the frequency of tooth rudiments absence ranges from 2 % to 16.5 %. The highest rank is held by maxillary lateral incisors hypodontia. Due the increased patients’ aesthetic requirements, it is a difficult task, especially with the alveolar ridge bone deficiency. Treatment of such patients requires a multidisciplinary approach and the use of digital technology. The aim of the study is to improve the treatment effectiveness for patients with hypodontia, using digital planning, surgical templates, intraoral scanning, and the CAD/CAM modelling of metal-free screw-retained crowns on dental implants. Materials and Methods. The clinical study was performed in the dental office PreziDent (Cheboksary) in 2018-2023. The total number of patients was 24 people (female), aged 16 to 34 years. There were two groups (n=12). The first group patients had their missing teeth replaced using dental implantation without using any digital technology. In the second group, those with the use of digital technologies. Gingival condition of the dentition defect area was assessed: Severity of stippling phenomenon degree, density gingival margin adherence to the structural materials, vacuum capillary resistance by Kulazhenko, and Mülleman-Cowell bleeding index. SPSS 13.0 software package was used for the statistical processing of the results obtained. Results and Discussion. The first stage of treatment included orthodontic treatment, bracket placement and canine distalization. Some patients were fitted with orthodontic miniscrews in the subclavicular region. After creating gaps for the future lateral incisors, a surgical template was fabricated and dental implants were placed. Four months after implantation, the bracket system was removed and the implant temporary crowns were placed; six months later, CAD/CAM digital metal-free prosthetics were placed. Not a single case of implant loss was detected. An algorithm framework was developed for managing patients with maxillary lateral incisor hypodontia. Conclusions. Using computer programs for planning dental implantation and in navigation surgery allows installing dental implants most accurately and making digital metal-free prosthetic constructions by computer-aided modelling and manufacturing. Thus, the risk of complications is reduced and an effective functional and aesthetic state of dentoalveolar system is achieved in patients with primary anodontia.