Training Costs Research Articles

OGC SO46 - Improving outcomes after oesophagectomy: The benefits of full robotic-assisted minimally invasive oesophagectomy (RAMIO) demonstrated in the first 100 cases, at a high-volume UK unit

Abstract Background There is a rapid movement towards adoption of robotically assisted minimally invasive oesophagectomy (RAMIO) in the United Kingdom. Transition from an open or laparoscopic oesophagectomy to a RAMIO programme, which carries considerable financial and training cost, must ensure parity of oncological and perioperative outcomes. We sought to compare our centre’s results of the three standard approaches to two-phase oesophagectomy: Open/Open (Open); laparoscopic/robotic abdomen with open chest (Hybrid); and RAMIO. Method This prospective cohort study investigated the experience of five surgeons in a single high-volume UK institution. We analysed consecutive patients undergoing two-phase transthoracic oesophagectomy for oncological reasons between 2018 and 2024. The study period was divided into three cohorts: Open (2018-2020, n=61), Hybrid (2020-2023, n=82) and RAMIO (2023-2024, n=100). Patient demographics, tumour characteristics, perioperative outcomes, and oncological data were compared. Data were analysed using Kruskal-Wallis and Chi-squared statistical tests. Results No significant differences were observed in patient demographics or tumour stage between the groups. Comparison of Open vs. Hybrid vs. RAMIO demonstrated a significant reduction in major complications (Clavien-Dindo ≥III), 34.4% vs. 23.2% vs. 14% (p=0.0014); pulmonary complications, 36.1% vs. 25.4% vs. 13% (p=0.0004); anastomotic leak rate, 11.5% vs. 2.4% vs. 4.0%, (p=0.0370); median length of stay, 14 vs. 12 vs. 8 days (p=0.0001); and mortality, 4.9% vs. 1.2% vs. 0% (p=0.0133) all favouring the RAMIO group in sub-group analysis. Median lymph node yields were comparable across groups, 49 vs. 43 vs. 43 (p=0.0876). Conclusion This single-institution study demonstrates potential benefits of transitioning from open or hybrid to RAMIO for oesophagectomy. RAMIO was associated with significantly reduced pulmonary complications, major complications and a shorter length of hospital stay. Oncological outcomes were maintained across all 3 techniques. These findings have important patient, financial, and resource implications, and support the continued adoption of RAMIO in the UK.

Cost analysis of adding hypertension and diabetes management into routine HIV care in Mbarara and Ibanda districts, Uganda.

In 2016, Uganda introduced services for hypertension and diabetes in selected HIV clinics. We evaluated the costs associated with scaling up these services in HIV clinics in Mbarara and Ibanda districts, Uganda. We estimated the annual costs of providing hypertension and diabetes services using an activity-based costing approach from the health system perspective in ten randomly selected HIV clinics in Mbarara and Ibanda districts. Cost inputs included 2023 data on costs of medications, health provider time, salaries, training costs, and monitoring costs. We determined the average annual cost and medication costs for hypertension and diabetes treatment per enrolled adult patient, stratified by type of health facility. The total annual cost of hypertension and diabetes management services in ten selected HIV clinics was estimated to be $413,850 (range: $8,386 - 186,973). The annual average clinic-level cost per enrolled patient was estimated at $14 (range: $7 - 31). Of the total annual cost, the cost of provider time for initial and follow-up visits represented the largest cost component in 5/10 clinics (mean: 37%, range [13-58%]). In 4/10 clinics, the major cost components were the costs of medication, diagnostic tests, and related supplies (mean: 37%, range [10-75%]). The average cost per enrolled adult patient was $11 at public facilities and $21 in private not-for-profit facilities. The average medication cost per patient for hypertension was $24 (range: $7 - 97) annually; $13 at public facilities and $50 at private not-for-profit facilities. For diabetes treatment, the average annual medication cost per patient was estimated at $14 (range: $6 - 35); $11 at public facilities and $22 at private not-for-profit facilities. Adding hypertension and diabetes management to routine HIV care might be feasible based on the estimated annual cost per patient. Hypertension and diabetes treatment was more costly in private not-for-profit facility-based clinics than at public facilities. This variation was primarily driven by higher medication procurement prices at private facilities, revealing a potential area for optimizing costs through improved procurement practices.

Research on the Principles and Applications of Generative Adversarial Networks in Image Style Transfer

Abstract. With the rapid development of machine learning, the field of image style transfer has received widespread attention, and scientists have gradually realized that this is an important field in computer vision. Image style transfer refers to the conversion of an image from one visual style to another and preserving the content. The technology of changing image style has a wide range of applications in various fields from art to virtual reality. Although current learning models have achieved some results in the study of image style transfer, they still face challenges in improving resolution and complex style transfer. This paper mainly introduces the background and characteristics of existing learning models that can achieve image style transfer. It introduces the principles, characteristics and limitations of GANs. In the basis of introduction, this paper also analyses the differences and different characteristics of GANs and summarizes the advantages and disadvantages of GANs. At the same time, this paper predicts future research directions, continuing to optimize these models, reducing training costs, and exploring hybrid methods to further advance image style transfer technology. These developments not only strengthen the theoretical research of image style transfer and GANs, but also have broad application potential in fields such as art, design and medical imaging.

Joint Mixing Data Augmentation for Skeleton-based Action Recognition

Skeleton-based action recognition is beneficial for understanding human behavior in videos, and thus has received much attention in recent years as an important research area in action recognition. Current research focuses on designing more advanced algorithms to better extract spatio-temporal information from skeleton data. However, due to the small amount of data in the existing skeleton dataset and the lack of effective data augmentation methods, it is easy to lead to overfitting in model training. To address this challenge, we propose a mix-based data augmentation method, Joint Mixing Data Augmentation (JMDA), which can generally improve the effectiveness and robustness of various skeleton-based action recognition algorithms. In terms of spatial information, we introduce SpatialMix (SM), a method that projects the original 3D skeleton discrete information into a 2D space. Then, SM mixes the projected spatial information between two random samples during the training process to achieve the spatial-based mixing data augmentation. Concerning temporal information, we propose TemporalMix (TM). Leveraging the temporal continuity in skeleton data, we perform a temporal resize operation on the original skeleton data, and then merge two random samples during training to achieve the temporal-based mixed data augmentation. Additionally, we analyze the Feature Mismatch (FM) problem caused by introducing mix-based data augmentation into skeleton data. Then we propose a new data preprocessing method called Feature Alignment (FA) to effectively address this problem and improve model performance. Moreover, we propose a novel training pipeline, Joint Training Strategy (JTS), which combines multiple mix-based data augmentation methods for further improvement of model performance. Specifically, our proposed JMDA is plug-and-play and widely applicable to skeleton-based action recognition models. At the same time, the application of JMDA does not increase the model parameters and there is almost no additional training cost. We conduct extensive experiments on NTU RGB+D 60 and NTU RGB+D 120 datasets to demonstrate the effectiveness and robustness of the proposed JMDA on several mainstream skeleton-based action recognition algorithms.

Cytometry masked autoencoder: An accurate and interpretable automated immunophenotyper.

Single-cell cytometry data are crucial for understanding the role of the immune system in diseases and responses to treatment. However, traditional methods for annotating cytometry data face challenges in scalability, robustness, and accuracy. We propose a cytometry masked autoencoder (cyMAE), which automates immunophenotyping tasks including cell type annotation. The model upholds user-defined cell type definitions, facilitating interpretability and cross-study comparisons. The training of cyMAE has a self-supervised phase, which leverages large amounts of unlabeled data, followed by fine-tuning on specialized tasks using smaller amounts of annotated data. The cost of training a new model is amortized over repeated inferences on new datasets using the same panel. Through validation across multiple studies using the same panel, we demonstrate that cyMAE delivers accurate and interpretable cellular immunophenotyping and improves the prediction of subject-level metadata. This proof of concept marks a significant step forward for large-scale immunology studies.

The effect of crop insurance on the financial risk of smallholder rice farmers in Cameroon

This study examined the effect of crop insurance on the financial risk of smallholder rice farmers in the grass field of Cameroon. Panel data from 76 Smallholder rice farming groups from 2019-2022 was used, while the Panel-corrected standard error technique was used for estimation. The results revealed that crop insurance captured using inputs (fertilizers, herbicides, and treated seeds) and land preparation had a positive and statistically significant effect on financial risk. These results validate the risk balancing hypothesis for smallholder rice farmers. Control variables like Farm size and labour had a positive and statistically significant effect, while training cost and buying price had a negative and statistically significant effect on financial risk. The results therefore, indicate that smallholder rice farmers need to adopt crop insurance practices such as use of quality farm inputs and better land preparation techniques in order to manage financial risk.

Efficient Multivariate Time Series Anomaly Detection Through Transfer Learning for Large-Scale Software Systems

Timely anomaly detection of multivariate time series (MTS) is of vital importance for managing large-scale software systems. However, many deep learning-based MTS anomaly detection models require long-term MTS training data to achieve optimal performance, which often conflicts with the frequent pattern changes observed in software systems. Moreover, the training overhead of vast MTS in large-scale software systems is unacceptably high. To address these issues, we design OmniTransfer , a model-agnostic framework that combines weighted hierarchical agglomerative clustering with an adaptive transfer learning strategy, making many state-of-the-art (SOTA) MTS anomaly detection models efficient and effective. Extensive experiments using real-world data from a large web content service provider and a network operator show that OmniTransfer significantly reduces the model initialization time by 46.49% and the training cost by 74.51%, while maintaining high accuracy in detecting anomalies.

HVASR: Enhancing 360-degree video delivery with viewport-aware super resolution

In recent years, 360-degree videos have gained significant traction due to their capacity to provide immersive experiences. However, the adoption of 360-degree videos substantially escalates bandwidth demands, necessitating approximately four to ten times more bandwidth than traditional video formats do. This presents a considerable challenge in maintaining high-quality videos in environments characterized by limited bandwidth or unstable networks. A trend has emerged where client-side computational power and deep neural networks are employed to enhance video quality while mitigating bandwidth requirements within contemporary video delivery systems. These approaches segment a video into discrete chunks and apply super resolution (SR) models to each segment, streaming low-resolution (LR) chunks alongside their corresponding SR models to the client. Although these methods enhance both video quality and transmission efficiency for conventional videos, they impose greater computational resource demands when applied to 360-degree content, thereby constraining widespread implementation. This paper introduces an innovative method called HVASR for 360-degree videos that leverages viewport information for more precise segmentation and minimizes model training costs as well as bandwidth requirements. Additionally, HVASR incorporates a viewport-aware training strategy that is aimed at further enhancing performance while reducing computational expenses. The experimental results demonstrate that HVASR achieves an average utility increase ranging from 12.46% to 40.89% across various scenes.

Investigation of hybrid modeling and its transferability in building load prediction used for district heating systems

In the district heating systems, the historical operation data of the buildings in those areas would be partially or entirely missing. The traditional data-driven model is hard to predict the ground truth results because the historical data is not available for model training. However, utilizing the physics-based methods for load calculation takes a long time to process and encounters low accuracy issues. This paper investigates several hybrid models that integrate the data-driven model and the physics-based models with different fusion methods. The physics-based models calculate envelope load and infiltration load, based on Fourier's law and the grand canonical ensemble theory, respectively. After undergoing load processing, features fusion, and residual connection, the best advanced hybrid models generate 21.35%, 16.35%, and 12.73% better prediction results compared with the data-driven model. Moreover, the advanced hybride models also perform strong transferability across all the data quantity groups. In terms of practical application, the advanced hybrid models could be deployed with effective generalization in limited data scenarios and robust transfer capabilities. The selected best model constructed by hybrid modeling displays the highest performance and saves the total training costs with strong transferability.

Economic impact case study of a wearable medical device for the diagnosis of obstructive sleep apnoea

BackgroundAcuPebble SA100 (‘AcuPebble’) is a novel wearable medical device to diagnose obstructive sleep apnoea (OSA). This paper investigates the potential economic impact of the technology in the UK through cost savings analysis, and the redirection of savings into further diagnoses.MethodsA cost comparison study was conducted, comparing AcuPebble to the standard diagnostic approach of home respiratory polygraphy (HRP) and in-clinic polysomnography (PSG), estimating the net benefit value (NBV) and return on investment (ROI). Cohort size was varied to model the effects of volume discounted pricing and staff training costs. To demonstrate the potential for cost savings, data on the healthcare costs of undiagnosed OSA patients were used to quantify the benefit of increased OSA diagnosis rates, as facilitated by AcuPebble.ResultsFor 500 uses of AcuPebble, the NBV in the diagnostic pathway over one year would be in excess of £101,169, increasing to £341,665 for 1,500 uses, £1,263,993 for 5,000 uses, and to £2,628,198 for 10,000 uses, with ROIs of 2.02, 3.03, 5.05, and 6.56, respectively. Given an initial cohort of 1,500 patients, 4,555 extra AcuPebble studies could be completed by redirecting resources from HRP/PSG. Direct cost savings to the NHS from resultant lower undiagnosed rates could be between £24,147 and £4,707,810, based on the cost per use and the percentage of tests that result in a positive diagnosis (varied from 25 to 75% positives).ConclusionsAcuPebble presents an opportunity for substantial healthcare savings, enabling an increase in the number of people tested, diagnosed and treated for OSA.

Cost-utility analysis of provision of e-cigarette starter kits for smoking cessation in emergency departments: An economic evaluation of a randomized controlled trial.

To assess the cost-effectiveness of the Cessation of Smoking Trial in Emergency Department (COSTED) intervention compared with signposting to local stop smoking service (SSS) from the National Health Service (NHS) and personal social services (PSS) perspective. This was a two-group, multi-centre, pragmatic, individually randomized controlled trial set in six Emergency Departments (EDs) in urban and rural areas in the United Kingdom. Adult (≥ 18 years) daily smokers (at least one cigarette or equivalent per day) but not daily e-cigarette users, with carbon monoxide reading ≥8parts per million, attending the ED (n= 972) were included. The intervention consisted of provision of an e-cigarette starter kit plus brief smoking cessation advice and referral to a local SSS. Control was an information card on how to access local SSS. Intervention costs included costs of training and delivery. Control costs included costs of printing information cards. Costs of smoking cessation and health-care services were estimated based on quantities reported by participants and unit costs extracted from secondary sources. The effects were measured by quality-adjusted life years (QALYs) derived from EQ-5D-5L. Other outcomes were smoking cessation measures. The primary outcome was incremental cost-effectiveness ratio (ICER), which was calculated by dividing the difference in costs by the difference in QALYs between groups. The mean intervention costs were £48 [standard error (SE) = £0] per participant and the mean control costs were £0.2 (SE = £0) per participant. Using regression estimates, total costs were £31 [95% confidence interval (CI) = -£341 to £283] higher and 6-month QALYs were 0.004 (95% CI = -0.004 to 0.014) higher in the intervention group than in the control group. The ICER was calculated at £7750 (probability of cost-effective at range £20 000-30 000: 72.2-76.5%). The UK Cessation of Smoking Trial in Emergency Department (COSTED) intervention (provision of an e-cigarette starter kit plus brief smoking cessation advice) was cost-effective compared with signposting to local stop smoking services under the current recommendations of the maximum acceptable thresholds.

Ratting on wildlife crime: training African giant pouched rats to detect illegally trafficked wildlife

The illegal wildlife trade (IWT) is one of the largest global crime economies, directly threatening species and their habitats, and biodiversity, and indirectly the global climate, and countries’ economies. Syndicates operating within the IWT are often involved in trafficking of humans, weapons, and drugs. IWT takes place in large scale through international ports, with wildlife being smuggled inside shipping containers. Current methods to combat IWT and screen these shipping containers, such as X-ray scans, are expensive and time-consuming. Scent-detection animals present an innovative approach to combatting IWT, as animals may be better suited to distinguish between organic materials and less susceptible to visual concealment methods. Previous scent-detection work has largely focused on conservation dogs (Canis lupus familiaris). Here, we present a series of proof-of-principle studies training African giant pouched rats (Cricetomys ansorgei) to detect illegally trafficked wildlife. As initial proof-of-principle within a controlled laboratory environment, we trained rats (n=11) to detect the scent of pangolin scales (Manis spp.) and a threatened African hardwood (Dalbergia melanoxylon). In subsequent experiments, we trained these rats (n=10) to detect rhinoceros horn (family Rhinocerotidae), and elephant tusks (Loxodonta spp.). At the conclusion of these studies, rats (n=7) accurately identified all four target species (although ivory samples may have been cross-contaminated, and results should be interpreted with caution) while correctly rejecting non-target items commonly used by traffickers to conceal the presence of illicit material. Rats detected the presence of wildlife targets even when these were concealed in mixtures among non-target items. These results provide the foundation to train rats for scent-detection of illegally trafficked wildlife to combat IWT. The unique attributes of rats could allow them to complement existing screening technologies in the fight against IWT. Rats have low training and maintenance costs, flexibly work with multiple handlers, have a long lifespan, and a sophisticated sense of smell. Their small size also offers unique capabilities for the screening of shipping containers, such as being able to navigate densely packed areas or be lifted to assess contents of sealed containers by screening ventilation systems. Future directions include assessing operational feasibility of deploying rats at ports.

Time-series water prediction based on feature clustering fusion and XGboost

Abstract. The time series prediction problem has a very wide range of applications in many fields. Most scholars use the LSTM class of algorithms for prediction. However, this method consumes a significant amount of computational power and presents several challenges. To address this issue, this paper proposes a time series forecasting method based on feature fusion and XGBoost. Specifically, we first utilize holiday information and the K-Means algorithm for feature extraction to expand the feature dimensions of the dataset, and then employ XGBoost as a model for training and prediction. Experiments demonstrate that the method proposed in this paper significantly reduces error compared to other traditional machine learning and deep learning methods, while the training time is much shorter than these methods. For example, compared with LSTM, the MSLE of this model decreases by 1.42%, while the training time is only 0.15% of that of LSTM. This greatly saves on training costs and computational power consumption. This confirms the effectiveness of using machine learning and clustering algorithms in time series prediction and provides new methods and practical application directions for future time series prediction models.

Review of physics-informed machine-learning inversion of geophysical data

We review five types of physics-informed machine-learning (PIML) algorithms for inversion and modeling of geophysical data. Such algorithms use the combination of a data-driven machine-learning (ML) method and the equations of physics to model or invert geophysical data (or both). By incorporating the constraints of physics, PIML algorithms can effectively reduce the size of the solution space for ML models, enabling them to be trained on smaller data sets. This is especially advantageous in scenarios in which data availability may be limited or expensive to obtain. In this review, we restrict the physics to be that from the governing wave equation, either as a constraint that must be satisfied or by using numerical solutions of the wave equation for modeling and inversion. This approach ensures that the resulting models adhere to physical principles while leveraging the power of ML to analyze and interpret complex geophysical data. There are several potential benefits of PIML compared to standard numerical modeling or inversion of seismic data computed by, for example, finite-difference solutions to the wave equation. 1) Empirical tests suggest that PIML algorithms constrained by the physics of wave propagation can sometimes resist getting stuck in a local minima compared with standard full-waveform inversion (FWI). 2) After the weights of the neural network are found by training, then the forward and inverse operations by PIML can be more than several orders of magnitude more efficient than FWI. However, the computational cost for general training can be enormous. 3) If the ML inversion operator [Formula: see text] is locally trained on a small portion of the recorded data [Formula: see text], then there is sometimes no need for millions of training examples that aim for global generalization of [Formula: see text]. The benefit is that the locally trained [Formula: see text] can be used to economically invert the remaining test data [Formula: see text] for the true velocity [Formula: see text], where [Formula: see text] can comprise more than 90% of the recorded data.

Cascade contour-enhanced panoptic segmentation for robotic vision perception.

Panoptic segmentation plays a crucial role in enabling robots to comprehend their surroundings, providing fine-grained scene understanding information for robots' intelligent tasks. Although existing methods have made some progress, they are prone to fail in areas with weak textures, small objects, etc. Inspired by biological vision research, we propose a cascaded contour-enhanced panoptic segmentation network called CCPSNet, attempting to enhance the discriminability of instances through structural knowledge. To acquire the scene structure, a cascade contour detection stream is designed, which extracts comprehensive scene contours using channel regulation structural perception module and coarse-to-fine cascade strategy. Furthermore, the contour-guided multi-scale feature enhancement stream is developed to boost the discrimination ability for small objects and weak textures. The stream integrates contour information and multi-scale context features through structural-aware feature modulation module and inverse aggregation technique. Experimental results show that our method improves accuracy on the Cityscapes (61.2 PQ) and COCO (43.5 PQ) datasets while also demonstrating robustness in challenging simulated real-world complex scenarios faced by robots, such as dirty cameras and rainy conditions. The proposed network promises to help the robot perceive the real scene. In future work, an unsupervised training strategy for the network could be explored to reduce the training cost.

Simplify to the Limit! Embedding-less Graph Collaborative Filtering for Recommender Systems

The tremendous positive driving effect of Graph Convolutional Network (GCN) and Graph Contrastive Learning (GCL) for recommender systems has become a consensus. GCN encoders are extensively used in recommendation models for capturing high-order connectivities between users and items, whereas GCL accelerates the training of recommendation tasks by adding extra supervision signals from contrastive objectives. However, little attention has been paid on corresponding theories that are truly tailored to recommendation tasks. From the technical perspective, Collaborative Filtering (CF) is seen as an important factor in recommender systems. It is applied to measure user-user, item-item, and user-item similarities rather than to achieve better clustering or node classification results. Besides, heuristic-based data augmentation may not be hold true in the field of recommender systems as it requires additional training costs and introduces noises that will corrupt the interaction graph structure and the semantic information of nodes. To tackle these limitations, we propose a novel Embedding-less Graph Collaborative Filtering (EGCF) for recommendation, which is tailor-made for the problem mentioned for CF and further simplifies existing solutions. Structurally, it consists of two parts: embedding-less GCN and embedding-less GCL. The former improves user-item affinity by streamlining user-type embeddings and carrying out iterative graph convolution. And the latter utilizes three-type contrastive objectives to directly measure the alignment and the uniformity of users, items, and interaction pairs, respectively, avoiding any type of data augmentation or multi-view construction. Even though EGCF has been extremely streamlined, extensive experimental results on three classical datasets demonstrate the effectiveness of EGCF in terms of recommendation accuracy and training efficiency. The code and used datasets are released at https://github.com/BlueGhostYi/ID-GRec.

Efficient Parameter Optimisation for Quantum Kernel Alignment: A Sub-sampling Approach in Variational Training

Quantum machine learning with quantum kernels for classification problems is a growing area of research. Recently, quantum kernel alignment techniques that parameterise the kernel have been developed, allowing the kernel to be trained and therefore aligned with a specific dataset. While quantum kernel alignment is a promising technique, it has been hampered by considerable training costs because the full kernel matrix must be constructed at every training iteration. Addressing this challenge, we introduce a novel method that seeks to balance efficiency and performance. We present a sub-sampling training approach that uses a subset of the kernel matrix at each training step, thereby reducing the overall computational cost of the training. In this work, we apply the sub-sampling method to synthetic datasets and a real-world breast cancer dataset and demonstrate considerable reductions in the number of circuits required to train the quantum kernel while maintaining classification accuracy.

Knowledge Graph Embedding for Hierarchical Entities Based on Auto-Embedding Size

Knowledge graph embedding represents entities and relations as low-dimensional continuous vectors. Recently, researchers have attempted to leverage the potential semantic connections between entities with hierarchical relationships in the knowledge graph. However, existing knowledge embedding methods that model entity hierarchical structures face the following challenges: (1) Setting the same embedding dimension for entities at different hierarchical levels can lead to overfitting issues and the waste of storage and computational resources; (2) Manually searching the embedding dimension in discrete space makes it easy to miss the optimal parameters and increases training costs. Therefore, we propose a knowledge embedding method, HEAES, that automatically learns the embedding dimensions for entities based on their hierarchical structure. Specifically, we first propose a new modeling method to capture the hierarchical relationships of entities, and we then train the model on a triple classification task. Then, we adaptively learn the pruning threshold to trim the embedding vectors, automatically learning different embedding dimensions for entities at different hierarchical levels. Experiments on the YAGO26K and DB111K datasets verify that introducing entity hierarchical information helps boost the model performance.

MobileNet-CAL: Tomato pest and disease classification method based on transfer learning and attention mechanism

Based on the MobileNetV3 model, this paper introduces the Coordinate attention (CA) attention mechanism and transfer learning to propose the MobileNet-CAL model to solve the problems of insufficient attention to model channel information, long classification training time, high training cost, and weak generalization ability. The model combines data enhancement, attention mechanism and transfer learning technology to improve the classification effect of the model, and updates the fully connected layer at the same time. Finally, the model is optimized by combining the Auxiliary loss function and the ASGD optimizer to improve the classification accuracy of the model, speed up the collection speed, and enhance the robustness of the model. Finally, the model is evaluated from multiple angles such as Accuracy, F1-score, Precision, Recall, and Specificity in the tomato pest and disease leaf dataset. Its Accuracy reaches 98.59% an accuracy of, which is improved by, and by, 4.47%respectively, compared with the original model. Experiments show that MobileNet-CAL can improve the classification accuracy to a certain extent, verifying that the model proposed 4.05%、3.43%、16.57% in 4.13%this paper is effective in the classification task of tomato pest and disease leaves.

Data-Driven Dynamic Security Partition Assessment of Power Systems Based on Symmetric Electrical Distance Matrix and Chebyshev Distance

A rapid dynamic security assessment (DSA) is crucial for online preventive and restoration decision-making. The deep learning-based DSA models have high efficiency and accuracy. However, the complex model structure and high training cost make them hard to update quickly. This paper proposes a dynamic security partition assessment method, aiming to develop accurate and incrementally updated DSA models with simple structures. Firstly, the power grid is self-adaptively partitioned into several local regions based on the mean shift algorithm. The input of the mean shift algorithm is a symmetric electrical distance matrix, and the distance metric is the Chebyshev distance. Secondly, high-level features of operating conditions are extracted based on the stacked denoising autoencoder. The symmetric electrical distance matrix is modified to represent fault locations in local regions. Finally, DSA models are constructed for fault locations in each region based on the radial basis function neural network (RBFNN) and Chebyshev distance. An online incremental updating strategy is designed to enhance the model adaptability. With the simulation software PSS/E 33.4.0, the proposed dynamic security partition assessment method is verified in a simplified provincial system and a large-scale practical system in China. Test results demonstrate that the Chebyshev distance can improve the partition quality of the mean shift algorithm by approximately 50%. The RBFNN-based partition assessment model achieves an accuracy of 98.96%, which is higher than the unified assessment with complex models. The proposed incremental updating strategy achieves an accuracy of over 98% and shortens the updating time to 30 s, which can meet the efficiency of online application.