Improvement In Accuracy Research Articles

Improvement The Accuracy of Convolutional Neural Network with Using Undersampling Method on Unbalanced Credit Card Dataset

In this study, we address the challenge of imbalanced data in credit card fraud detection by proposing a novel approach that leverages Convolutional Neural Networks (CNNs) and undersampling techniques. The imbalance in the dataset, typical of real-world financial transactions, often leads to biased models favoring the majority class. To mitigate this, we employ undersampling to balance the classes, thereby enhancing the CNN's ability to learn from minority instances crucial for fraud detection. Our method is validated on a large unbalanced credit card dataset, demonstrating significant improvements in accuracy compared to traditional CNN models trained on imbalanced data. We evaluate our approach using standard performance metrics, including precision, recall, and F1-score, showcasing its effectiveness in accurately identifying fraudulent transactions while minimizing false positives. Furthermore, we pro-vide insights into the CNN's decision-making process through visualization techniques, shedding light on its ability to discern fraudulent patterns within the data. Our findings highlight the importance of addressing class imbalance in fraud detection tasks and underscore the efficacy of undersampling in enhancing the performance of deep learning models, particularly CNNs, in handling imbalanced datasets.

LFformer: An improved Transformer model for wind power prediction.

Wind power forecasting has complex nonlinear features and behavioral patterns across time scales, which is a severe test for traditional forecasting techniques. To address the multi-scale problem in wind power forecasting, this paper innovatively proposes an ultra-short-term forecasting model LFformer based on Legendre-Fourier, which firstly focuses on the important information in the input sequences by using the encoder-decoder architecture, and then scales the range of the original data with the Devlin normalization method, and then utilizes the Legendre polynomials to The data sequence is projected into a bounded dimensional space, the historical data is compressed using feature representation, then feature selection is performed using the low-rank approximation method of Fourier Transform, the prediction is inputted into the multilayer perceptron through the multi-scale mixing mechanism, and finally the results are outputted after back-normalization. The experimental results show that compared with the existing prediction methods, the model realizes the improvement of prediction accuracy and stability, especially in the ultra-short-term prediction scenario, with obvious advantages. The research results are not only valuable for improving the overall operational efficiency of the wind power system, but also help to enhance the stable operation of the power grid, which provides strong technical support and guarantee for wind power enterprises to improve the competitiveness of bidding for Internet access in the power market competition.

Research on tire internal defect identification method based on deep learning

As an important part of automobile, the safety and durability of tire have attracted more and more attention. Tire defect detection is an important link to ensure tire quality, while traditional detection methods have problems such as low efficiency, high false detection rate and high labor intensity. Therefore, this study aims to develop an efficient and accurate tire defect identification and classification technique to improve the efficiency and accuracy of tire inspection. In this paper, based on YOLO (You Only Look Once) v5 algorithm, tire defect recognition and classification are studied. Firstly, the data sets containing various types of tire defects were collected and sorted out, and the data sets were preprocessed. Then, by constructing, training and optimizing the YOLOv5 tire defect recognition model, the fast and accurate recognition of tire defects was realized. Finally, the performance of the model was evaluated through experiments and compared with the existing methods. The experimental results show that the tire defect recognition and classification method based on YOLOv5 proposed in this study has high accuracy. Compared with traditional methods, this method has a significant improvement in detection speed and accuracy.

Trajectory error compensation method for grinding robots based on kinematic calibration and joint variable prediction

Trajectory accuracy, a crucial metric in assessing the dynamic performance of grinding robots, is influenced by the uncertain movement of the tool center point, directly impacting the surface quality of processed workpieces. This article introduces an innovative method for compensating trajectory errors. Initially, a strategy for error compensation is derived using differential kinematics theory. Subsequently, a robot kinematic calibration method utilizing ring particle swarm optimization (RPSO) is proposed to address static errors in the grinding robot. Simultaneously, a method for predicting robot joint variables based on a dual-channel feedforward neural network (DCFNN) is designed to mitigate dynamic errors. Finally, a simulation platform is developed to validate the proposed method. Simulation analysis using extensive data demonstrates an 89.3% improvement in absolute position accuracy and a 74.2% reduction in error fluctuation range, outperforming sparrow search algorithm (SSA), improved mayfly algorithm (IMA), multi-representation integrated predictive neural network (MRIPNN), etc. Algorithmic comparison reveals that kinematic calibration significantly reduces the average trajectory error, while joint variable prediction notably minimizes error fluctuation. Validation through trajectory straightness testing and a 3D printing propeller grinding experiment achieves a trajectory straightness of 0.2425 mm. Implementing this method enables achieving 86.1% surface machining allowance within tolerance, making it an optimal solution for grinding robots.

Feature detection of B-ultrasound images of intussusception in children based on improved YOLOv8n

To assist grassroots sonographers in accurately and rapidly detecting intussusception lesions from children's abdominal ultrasound images, this paper proposes an improved YOLOv8n children's intussusception detection algorithm, called EMC-YOLOv8n. Firstly, the EfficientViT network with a cascaded group attention module was used as the backbone network to enhance the speed of target detection. Secondly, the improved C2fMBC module was used to replace the C2f module in the neck network to reduce network complexity, and the coordinate attention (CA) module was introduced after each C2fMBC module to enhance attention to positional information. Finally, experiments were conducted on the self-built dataset of intussusception in children. The results showed that the recall rate, average detection accuracy (mAP@0.5) and precision of the EMC-YOLOv8n algorithm improved by 3.9%, 2.1% and 0.9%, respectively, compared to the baseline algorithm. Despite slightly increased network parameters and computational load, significant improvements in detection accuracy enable efficient completion of detection tasks, demonstrating substantial economic and social value.

PERANCANGAN SISTEM ENTERPRISE RESOURCE PLANNING (ERP) TERHADAP PENGADAAN BAHAN BAKU, PENJUALAN, DAN PRODUKSI PADA CV. JAYA LOGAM MENGGUNAKAN SOFTWARE ODOO

CV. Jaya Logam faced various operational challenges caused by ineffective sales and raw material inventory recording systems, leading to production delays, errors in information delivery, and difficulties in monitoring and decision-making. This research was conducted to address these issues through system needs analysis, design, and testing of an Enterprise Resource Planning (ERP) system using Odoo software. The methodological process involved a detailed analysis of system requirements, system design using Unified Modelling Language (UML) diagrams to visualize the system architecture, and system testing using the Black Box Testing method to ensure the reliability and effectiveness of the designed system. The testing results showed that the developed ERP system successfully met all 12 test class parameters, indicating that the system is valid and can be implemented effectively. The implementation of this ERP system at CV. Jaya Logam resulted in significant improvements in operational efficiency and data accuracy, better business process integration, and the provision of real-time information that supports faster and more accurate decision-making processes.

OUCH: Oversampling and Undersampling Cannot Help Improve Accuracy in Our Bayesian Classifiers That Predict Preeclampsia

Unbalanced data can have an impact on the machine learning (ML) algorithms that build predictive models. This manuscript studies the influence of oversampling and undersampling strategies on the learning of the Bayesian classification models that predict the risk of suffering preeclampsia. Given the properties of our dataset, only the oversampling and undersampling methods that operate with numerical and categorical attributes will be taken into consideration. In particular, synthetic minority oversampling techniques for nominal and continuous data (SMOTE-NC), SMOTE—Encoded Nominal and Continuous (SMOTE-ENC), random oversampling examples (ROSE), random undersampling examples (UNDER), and random oversampling techniques (OVER) are considered. According to the results, when balancing the class in the training dataset, the accuracy percentages do not improve. However, in the test dataset, both positive and negative cases of preeclampsia were accurately classified by the models, which were built on a balanced training dataset. In contrast, models built on the imbalanced training dataset were not good at detecting positive cases of preeclampsia. We can conclude that while imbalanced training datasets can be addressed by using oversampling and undersampling techniques before building prediction models, an improvement in model accuracy is not always guaranteed. Despite this, the sensitivity and specificity percentages improve in binary classification problems in most cases, such as the one we are dealing with in this manuscript.

DNA-protein quasi-mapping for rapid differential gene expression analysis in non-model organisms

BackgroundConventional differential gene expression analysis pipelines for non-model organisms require computationally expensive transcriptome assembly. We recently proposed an alternative strategy of directly aligning RNA-seq reads to a protein database, and demonstrated drastic improvements in speed, memory usage, and accuracy in identifying differentially expressed genes.ResultHere we report a further speed-up by replacing DNA-protein alignment by quasi-mapping, making our pipeline > 1000× faster than assembly-based approach, and still more accurate. We also compare quasi-mapping to other mapping techniques, and show that it is faster but at the cost of sensitivity.ConclusionWe provide a quick-and-dirty differential gene expression analysis pipeline for non-model organisms without a reference transcriptome, which directly quasi-maps RNA-seq reads to a reference protein database, avoiding computationally expensive transcriptome assembly.

Application of Hybrid Attention Mechanisms in Lithological Classification with Multisource Data: A Case Study from the Altay Orogenic Belt

Multisource data fusion technology integrates the strengths of various data sources, addressing the limitations of relying on a single source. Therefore, it has been widely applied in fields such as lithological classification and mineral exploration. However, traditional deep learning algorithms fail to distinguish the importance of different features effectively during fusion, leading to insufficient focus in the model. To address this issue, this paper introduces a ResHA network based on a hybrid attention mechanism to fuse features from ASTER remote sensing images, geochemical data, and DEM data. A case study was conducted in the Altay Orogenic Belt to demonstrate the lithological classification process. This study explored the impact of the submodule order on the hybrid attention mechanism and compared the results with those of MLP, KNN, RF, and SVM models. The experimental results show that (1) the ResHA network with hybrid attention mechanisms assigned reasonable weights to the feature sets, allowing the model to focus on key features closely related to the task. This resulted in a 7.99% improvement in classification accuracy compared with that of traditional models, significantly increasing the precision of lithological classification. (2) The combination of channel attention followed by spatial attention achieved the highest overall accuracy, 98.06%.

High Energy Density Radiative Transfer in the Diffusion Regime with Fourier Neural Operators

AbstractRadiative heat transfer is a fundamental process in high energy density physics and inertial fusion. Accurately predicting the behavior of Marshak waves across a wide range of material properties and drive conditions is crucial for design and analysis of these systems. Conventional numerical solvers and analytical approximations often face challenges in terms of accuracy and computational efficiency. In this work, we propose a novel approach to model Marshak waves using Fourier Neural Operators (FNO). We develop two FNO-based models: (1) a base model that learns the mapping between the drive condition and material properties to a solution approximation based on the widely used analytic model by Hammer & Rosen (2003), and (2) a model that corrects the inaccuracies of the analytic approximation by learning the mapping to a more accurate numerical solution. Our results demonstrate the strong generalization capabilities of the FNOs and show significant improvements in prediction accuracy compared to the base analytic model.

PcMNet: An efficient lightweight apple detection algorithm in natural orchards

Apple detection plays a critical role in enabling the functionality of harvesting robots within natural orchard environments. To address challenges related to low detection accuracy, slow inference speed, and high parameter count, we present PcMNet, a lightweight detection model based on an improved YOLOv8 network. Initially, we employed Partial Convolution (Pconv) to construct a PR module, forming the Pconv-block, which subsequently replaced the original C2f feature extraction module within the YOLOv8n backbone. This replacement led to improvements in both detection accuracy and speed, while simultaneously reducing computational complexity (FLOPs), parameter count, and model size. Furthermore, the Cross-Scale Feature Fusion (CCFF) module was refined into Faster-Cross-Scale Feature Fusion (Faster-CCFF) with the integration of Pconv-block, significantly enhancing the model's feature extraction and fusion capabilities. Additionally, we introduced Mixed Local Channel Attention (MLCA) to further strengthen the model's capacity to capture essential features while effectively suppressing background noise. Experimental results demonstrate that PcMNet achieved a detection accuracy of 92.8 % and an mAP@0.5 of 95.5 %, representing improvements of 1.4 and 0.7 percentage points, respectively, over YOLOv8n. Moreover, PcMNet successfully reduced FLOPs, parameter count, and model size to 5.1 G, 1.4 M, and 3.2 MB, respectively. The per-image detection time was reduced to 2.3 ms, indicating reductions of 37.80 %, 53.33 %, 49.21 %, and 56.60 % in FLOPs, parameters, model size, and detection time compared to YOLOv8n. When deployed on edge computing devices with TensorRT acceleration, PcMNet achieved a detection rate of 92 FPS. Field validation experiments conducted in natural orchard environments confirmed PcMNet's superior ability to detect apples under challenging conditions, such as occlusions and varying lighting conditions. Its lightweight design and rapid detection capabilities provide a valuable reference for achieving real-time apple detection in automated and intelligent harvesting robots, thereby contributing to advancements in smart agriculture.

Stereo and LiDAR Loosely Coupled SLAM Constrained Ground Detection.

In many robotic applications, creating a map is crucial, and 3D maps provide a method for estimating the positions of other objects or obstacles. Most of the previous research processes 3D point clouds through projection-based or voxel-based models, but both approaches have certain limitations. This paper proposes a hybrid localization and mapping method using stereo vision and LiDAR. Unlike the traditional single-sensor systems, we construct a pose optimization model by matching ground information between LiDAR maps and visual images. We use stereo vision to extract ground information and fuse it with LiDAR tensor voting data to establish coplanarity constraints. Pose optimization is achieved through a graph-based optimization algorithm and a local window optimization method. The proposed method is evaluated using the KITTI dataset and compared against the ORB-SLAM3, F-LOAM, LOAM, and LeGO-LOAM methods. Additionally, we generate 3D point cloud maps for the corresponding sequences and high-definition point cloud maps of the streets in sequence 00. The experimental results demonstrate significant improvements in trajectory accuracy and robustness, enabling the construction of clear, dense 3D maps.

Sample feature enhancement model based on heterogeneous graph representation learning for few-shot relation classification

Few-Shot Relation Classification (FSRC) aims to predict novel relationships by learning from limited samples. Graph Neural Network (GNN) approaches for FSRC constructs data as graphs, effectively capturing sample features through graph representation learning. However, they often face several challenges: 1) They tend to neglect the interactions between samples from different support sets and overlook the implicit noise in labels, leading to sub-optimal sample feature generation. 2) They struggle to deeply mine the diverse semantic information present in FSRC data. 3) Over-smoothing and overfitting limit the model's depth and adversely affect overall performance. To address these issues, we propose a Sample Representation Enhancement model based on Heterogeneous Graph Neural Network (SRE-HGNN) for FSRC. This method leverages inter-sample and inter-class associations (i.e., label mutual attention) to effectively fuse features and generate more expressive sample representations. Edge-heterogeneous GNNs are employed to enhance sample features by capturing heterogeneous information of varying depths through different edge attentions. Additionally, we introduce an attention-based neighbor node culling method, enabling the model to stack higher levels and extract deeper inter-sample associations, thereby improving performance. Finally, experiments are conducted for the FSRC task, and SRE-HGNN achieves an average accuracy improvement of 1.84% and 1.02% across two public datasets.

Development and evaluation of a novel framework to enhance k-NN algorithm’s accuracy in data sparsity contexts

This paper presents a novel framework for implementing the k-NN algorithm, designed to enhance its accuracy in contexts with sparse data. The framework addresses limitations in the algorithm’s training process by optimizing data structures. It employs composite datasets generated from the initial data using a data-driven fuzzy Analytic Hierarchy Process weighting scheme. This approach is designed to enhance the informational content in the initial datasets, thus reducing the entropy and implementation uncertainty. The framework was evaluated using 75 publicly available datasets and 3 generated datasets, demonstrating significant accuracy improvements across various k-parameter values. The findings were rigorously generalized using non-parametric hypothesis tests; while the resulting sensitivity was assessed by applying different distance metrics. By enhancing informational content, the composite data structures contribute to both accuracy improvements and scalability, particularly in data-sparse contexts. This relationship underscores the critical role of entropy in enhancing the performance of explainable machine learning algorithms, providing a valuable and interpretable tool for transforming data structures in sparse data environments.

Enhancing Smart Grid Stability through a Hybrid Biometric Pattern Recognition and Long Short-Term Memory Approach

The stability of power grids is critical in ensuring the consistent and efficient delivery of electricity. However, traditional predictive models often fall short in addressing grid data's intricate and ever-changing nature, making it challenging to maintain grid reliability. This paper introduces a novel hybrid approach that combines Biometric Pattern Recognition (BPR) with Long Short-Term Memory (LSTM) networks to enhance the prediction of smart grid stability. This approach employs BPR techniques to extract essential features from smart grid data by leveraging the pattern recognition capabilities typically used in biometric systems. These techniques are particularly effective in identifying and isolating the most relevant patterns within the complex datasets generated by smart grids. On the other hand, the LSTM-based model is designed to handle the temporal dependencies and nonlinear patterns characteristic of grid data. LSTMs, known for their proficiency in time-series analysis, are well-suited for capturing the sequential nature of grid data, enabling more accurate predictions over time. Integrating BPR and LSTM in this hybrid model addresses several limitations in existing predictive methods. By combining the strengths of both techniques, the model enhances the accuracy of predictions and improves the overall reliability of grid stability assessments. Extensive experiments were conducted using real-world datasets to validate the effectiveness of the proposed hybrid model. The results demonstrate a significant improvement in prediction accuracy, with the BPR-LSTM model achieving a 98.25% increase in accuracy compared to traditional prediction methods. This improvement underscores the potential of the BPR-LSTM hybrid approach to play a pivotal role in advancing the stability and reliability of smart grid systems.

Liquid Metal-Based Elastomer Composite with Selective Switchable Adhesion to Solids.

Selective switchable adhesion has recently attracted much attention due to its wide applications in transfer printing, information transfer, and flexible electronics. However, selective adhesive materials often have a complex adhesion or preparation process, which limits their use. To overcome this problem, this study prepares a composite of liquid metal foam and polydimethylsiloxane (PDMS) with selective photocontrolled adhesion, which can directly adhere to solids at room temperature. Utilizing the photoinduced phase transition of liquid metals, solid adhesion can be regulated by changing the backing layer modulus of the adhesive layer. Since the phase transition process is gradually completed by heat transfer from the illuminated side to the backlight side that adheres to the solid, the melting area on the backlight side can be regulated by controlling the light time, which determines the adhesion regulation area. Therefore, the accuracy of the adhesion regulation can reach less than 0.9 mm without relying on the accuracy of the infrared light. Moreover, based on the selective switchable adhesion, the selective transfer of solids with different scales can be achieved at room temperature. The findings of this study may provide strategies for the simple preparation of selective adhesive materials and the improvement of control accuracy.

Optimized Soil Moisture Mapping Strategies on the Tibetan Plateau Using Downscaled and Interpolated Maps as Mutual Covariates

Accurate high-resolution soil moisture maps are crucial for a better understanding of hydrological processes and energy cycles. Mapping strategies such as downscaling and interpolation have been developed to obtain high-resolution soil moisture maps from multi-source inputs. However, research on the optimization performance of integrating downscaling and interpolation, especially through the use of mutual covariates, remains unclear. In this study, we compared four methods—two standalone methods based on downscaling and interpolation strategies and two combined methods that utilize soil moisture maps as mutual covariates within each strategy—in a case study of daily soil moisture mapping at a 1 km resolution in the Tibetan Plateau. We assessed mapping performance in terms of prediction accuracy and differences in spatial coverage. The results indicated that introducing interpolated soil moisture maps into the downscaling strategy significantly improved prediction accuracy (RMSE: −5.94%, correlation coefficient: +14.02%) but was limited to localized spatial coverage (6.9% of grid cells) near in situ sites. Conversely, integrating downscaled soil moisture maps into the interpolation strategy resulted in only modest gains in prediction accuracy (RMSE: −1.07%, correlation coefficient: +1.04%), yet facilitated broader spatial coverage (40.4% of grid cells). This study highlights the critical differences between downscaling and interpolation strategies in terms of accuracy improvement and spatial coverage, providing a reference for optimizing soil moisture mapping over large areas.

Knowledge-injected Prompt Learning for Chinese Biomedical Entity Normalization

The Biomedical Entity Normalization (BEN) task aims to align raw, unstructured medical entities to standard entities, thus promoting data coherence and facilitating better downstream medical applications. Recently, prompt learning methods have shown promising results in the natural language processing field. However, existing research falls short in tackling the more complex Chinese BEN task, especially in the few-shot scenario with limited medical data, and the vast potential of the external medical knowledge base has not yet been fully exploited. To address these challenges, this article proposes a novel Knowledge-injected Prompt Learning (PL-Knowledge) method. Specifically, the approach consists of five stages: candidate entity matching, knowledge extraction, knowledge encoding, knowledge injection, and prediction output. By effectively encoding the knowledge items contained in medical entities and incorporating them into tailor-made knowledge-injected templates, the additional knowledge enhances the model’s ability to capture latent relationships between medical entities, thus achieving a better match with the standard entities. Comprehensive experiments are conducted on a benchmark dataset in both few-shot and full-scale settings. This method outperforms existing baselines, with an average accuracy improvement of 12.96 percentage points in few-shot and 0.94 percentage points in full-data cases, showcasing its excellence in the BEN task.

Theoretical analysis of water-droplet condensation and evaporation in prescribed environment with radiation

Abstract A quasi-explicit algebraic solution of the problem of quasi-steady water droplet heat- and mass-transfer with condensation or evaporation in a prescribed environment including radiation has been obtained. The solution is based on the mass-fraction form of Fick’s law of species diffusive mass transport, which allows accounting for variation in gas density through the diffusion layer surrounding the droplet. A new term, the average vapor supersaturation through the diffusion layer, has been included that allows the model to be extended to environmental conditions significantly outside those for which it is theoretically derived (dilute or near-saturation), even to conditions of relatively high temperature, low relative humidity, and low pressure. The latter two have atmospheric significance because evaporative cooling can induce significant decrease in droplet temperature and possibly induce freezing. Basic modeling assumptions are confirmed by comparison with time-dependent temperature and evaporation-rate measurements of a laboratory laser-heated droplet. Accuracy of the new model is assessed by comparison with exact equations. For temperatures between −30 and 0°C and negligible radiation, relative-error magnitudes in droplet temperature and evaporation rate are less than 5%, even for relative humidity down to 10% and pressure down to 60 kPa. This represents an improvement in accuracy over the conventional model, in which property variations of density and supersaturation through the diffusion layer are not taken into account. Differences in predicted evaporation rates between the mass-fraction and the more common partial-density Fick’s laws, which can be significant (>10% above 70% relative humidity) in coupled, implicit equations, are shown to be made negligibly small (<0.5%) by linearizing about the saturation state.

Post-earthquake inspection of high-speed railway viaducts with multi-scale task interaction deep learning strategy

Automated computer vision-based inspections of railway infrastructures, such as component type, damaged status, and location, have been investigated actively by resorting to task-specific deep learning models. However, task-specific models that fulfill these separate inspection tasks encountered bottlenecks in improving inference accuracy, and bring huge computational costs. Multi-task deep learning, which can fulfill these inspection tasks concurrently, has yet to be fully investigated in the context of structural inspection. In this study, a multi-scale task interaction deep learning strategy is presented towards component recognition, damage segmentation, and depth estimation for a comprehensive post-earthquake inspection of high-speed railway viaducts. Three modules for multi-scale task interaction were proposed to modify the multi-task deep neural network, taking full advantage of task commonalities at multiple scales. The proposed method was validated with a large-scale image dataset of high-speed railway viaducts. Component recognition and depth estimation were incorporated to implement multi-task learning since they have higher pattern affinities at multiple scales. Results reported that mean Intersection over Unions of testing samples of component and damage tasks were 91.2% and 72.1%, RMSE of depth estimation was 1.54 m. Compared with single-task cases, training time, inference duration, and FLOPs of the multi-task model were reduced by 23%, 30%, 27% respectively. Results showed improvement in both inference accuracy and training efficiency, substantiating the superiority of the proposed strategy.