Classification Efficiency Research Articles

Ensemble Learning Improves the Efficiency of Microseismic Signal Classification in Landslide Seismic Monitoring.

A deep-seated landslide could release numerous microseismic signals from creep-slip movement, which includes a rock-soil slip from the slope surface and a rock-soil shear rupture in the subsurface. Machine learning can effectively enhance the classification of microseismic signals in landslide seismic monitoring and interpret the mechanical processes of landslide motion. In this paper, eight sets of triaxial seismic sensors were deployed inside the deep-seated landslide, Jiuxianping, China, and a large number of microseismic signals related to the slope movement were obtained through 1-year-long continuous monitoring. All the data were passed through the seismic event identification mode, the ratio of the long-time average and short-time average. We selected 11 days of data, manually classified 4131 data into eight categories, and created a microseismic event database. Classical machine learning algorithms and ensemble learning algorithms were tested in this paper. In order to evaluate the seismic event classification performance of each algorithmic model, we evaluated the proposed algorithms through the dimensions of the accuracy, precision, and recall of each model. The validation results demonstrated that the best performing decision tree algorithm among the classical machine learning algorithms had an accuracy of 88.75%, while the ensemble algorithms, including random forest, Gradient Boosting Trees, Extreme Gradient Boosting, and Light Gradient Boosting Machine, had an accuracy range from 93.5% to 94.2% and also achieved better results in the combined evaluation of the precision, recall, and F1 score. The specific classification tests for each microseismic event category showed the same results. The results suggested that the ensemble learning algorithms show better results compared to the classical machine learning algorithms.

An Empirical Study on the Upcycling of Glass Bottles into Hydrocyclone Separators

Cyclones are pivotal in mechanical process engineering and crucial in the complex field of separation technology. Their robustness and compact spatial requirements render them universally applicable and versatile across various industrial domains. Depending on the utilized fluid and field of application, both gas-based cyclones and hydrocyclones (HCs) are well established. Regarding HC design, enduring elongated flat cones have seen minimal alterations in shape and structure since their introduction over more than a hundred years ago. Experimental investigations regarding unconventional cone designs within scientific studies remain the exception. Therefore, this study focuses on alternative geometric configurations of the separation chambers and highlights their impact on separation and energy efficiency. To achieve this objective, different geometric shapes are investigated and retrofitted into HCs. The geometric foundation is derived from upcycled glass bottles. The repurposed bottles with a volume of 750 mL are used in conjunction with an inlet part, following the established Rietema design. Experimental tests are conducted with dilute phase separation, using 0.1–200 µm test particles in water. Comparisons between a bottle-based HC and a conventional Rietema design were conducted, establishing a benchmark against the standard. The findings revealed a noticeable correlation between separation efficiency and cone geometry. Conical designs demonstrated enhanced separation, particularly at lower volume flows. At the highest volume flow of 75 L min−1, the best performing bottle cyclones showed separation efficiencies of 78.5%, 78.4% and 77.9% and therefore are in a competitive range with 78.0% efficiency, achieved using the commercial Rietema design. Minimal disparities in cut sizes were observed in terms of separation grade efficiency among the models tested. Variations in separation efficiency and fractional efficiency curves indicated nuanced differences in classification efficiency.

Parkinson's image detection and classification based on deep learning

ObjectiveThere are two major issues in the MRI image diagnosis task for Parkinson's disease. Firstly, there are slight differences in MRI images between healthy individuals and Parkinson's patients, and the medical field has not yet established precise lesion localization standards, which poses a huge challenge for the effective prediction of Parkinson's disease through MRI images. Secondly, the early diagnosis of Parkinson's disease traditionally relies on the subjective judgment of doctors, which leads to insufficient accuracy and consistency. This article proposes an improved YOLOv5 detection algorithm based on deep learning for predicting and classifying Parkinson's images.MethodsThis article improves the YOLOv5s network as the basic framework. Firstly, the CA attention mechanism was introduced to enable the model to dynamically adjust attention based on local features of the image, significantly enhancing the sensitivity of the model to PD related small pathological features; Secondly, replace the dynamic full dimensional convolution module to optimize the multi-level extraction of image features; Finally, the coupling head strategy is adopted to improve the execution efficiency of classification and localization tasks separately.ResultsWe validated the effectiveness of the proposed method using a dataset of 582 MRI images from 108 patients. The results show that the proposed method achieves 0.961, 0.974, and 0.986 in Precision, Recall, and mAP, respectively, and the experimental results are superior to other algorithms.ConslusionThe improved model has achieved high accuracy and detection accuracy, and can accurately detect and recognize complex Parkinson's MRI images.SignificanceThis algorithm has shown good performance in the early diagnosis of Parkinson's disease and can provide clinical assistance for doctors in early diagnosis. It compensates for the limitations of traditional methods.

Research on Model Selection-Based Weighted Averaged One-Dependence Estimators

The Averaged One-Dependence Estimators (AODE) is a popular and effective method of Bayesian classification. In AODE, selecting the optimal sub-model based on a cross-validated risk minimization strategy can further enhance classification performance. However, existing cross-validation risk minimization strategies do not consider the differences in attributes in classification decisions. Consequently, this paper introduces an algorithm for Model Selection-based Weighted AODE (SWAODE). To express the differences in attributes in classification decisions, the ODE corresponding to attributes are weighted, with mutual information commonly used in the field of machine learning adopted as weights. Then, these weighted sub-models are evaluated and selected using leave-one-out cross-validation (LOOCV) to determine the best model. The new method can improve the accuracy and robustness of the model and better adapt to different data features, thereby enhancing the performance of the classification algorithm. Experimental results indicate that the algorithm merges the benefits of weighting with model selection, markedly enhancing the classification efficiency of the AODE algorithm.

A Dual-Branch Fusion of a Graph Convolutional Network and a Convolutional Neural Network for Hyperspectral Image Classification.

Semi-supervised graph convolutional networks (SSGCNs) have been proven to be effective in hyperspectral image classification (HSIC). However, limited training data and spectral uncertainty restrict the classification performance, and the computational demands of a graph convolution network (GCN) present challenges for real-time applications. To overcome these issues, a dual-branch fusion of a GCN and convolutional neural network (DFGCN) is proposed for HSIC tasks. The GCN branch uses an adaptive multi-scale superpixel segmentation method to build fusion adjacency matrices at various scales, which improves the graph convolution efficiency and node representations. Additionally, a spectral feature enhancement module (SFEM) enhances the transmission of crucial channel information between the two graph convolutions. Meanwhile, the CNN branch uses a convolutional network with an attention mechanism to focus on detailed features of local areas. By combining the multi-scale superpixel features from the GCN branch and the local pixel features from the CNN branch, this method leverages complementary features to fully learn rich spatial-spectral information. Our experimental results demonstrate that the proposed method outperforms existing advanced approaches in terms of classification efficiency and accuracy across three benchmark data sets.

ICS-ResNet: A Lightweight Network for Maize Leaf Disease Classification

The accurate identification of corn leaf diseases is crucial for preventing disease spread and improving corn yield. Plant leaf images are often affected by factors such as complex backgrounds, climate, light, and sample data imbalance. To address these issues, we propose a lightweight convolutional neural network, ICS-ResNet, based on ResNet50. This network incorporates improved spatial and channel attention modules as well as a deep separable residual structure to enhance recognition accuracy. (1) The residual connections in the ResNet network prevent gradient loss during deep network training. (2) The improved channel attention (ICA) and spatial attention (ISA) modules fully utilize semantic information from different feature layers to accurately localize key features of the network. (3) To reduce the number of parameters and lower computational costs, we replace traditional convolutional computation with a depth-separable residual structure. (4) We also employ cosine annealing to dynamically adjust the learning rate, enhancing the network’s training stability, improving model convergence, and preventing local optima. Experiments on the corn dataset in Plant Village compare the proposed ICS-ResNet with eight popular networks: CSPNet, InceptionNet_v3, EfficientNet, ShuffleNet, MobileNet, ResNet50, ResNet101 and ResNet152. The results show that the ICS-ResNet achieves an accuracy of 98.87%, which is 5.03%, 3.18%, 1.13%, 1.81%, 1.13%, 0.68%, 0.44% and 0.60% higher than the other networks, respectively. Furthermore, the number of parameters and computations are reduced by 69.21% and 54.88%, respectively, compared to the original ResNet50 network, significantly improving the efficiency of corn leaf disease classification. The study provides strong technical support for sustainable agriculture and the promotion of agricultural science and technology innovation.

Optimizing feedforward neural networks using a modified weighted mean of vectors: Case study chemical datasets

This paper proposes a modified version of the weighted mean of vectors algorithm (mINFO), which combines the strengths of the INFO algorithm with the Enhanced Solution Quality Operator (ESQ). The ESQ boosts the quality of the solutions by avoiding optimal local values, verifying that each solution moves towards a better position, and increasing the convergence speed. Furthermore, we employ the mINFO algorithm to optimize the connection weights and biases of feedforward neural networks (FNNs) to improve their accuracy. The efficacy of FNNs for classification tasks is mainly dependent on hyperparameter tuning, such as the number of layers and nodes. The mINFO was evaluated using the IEEE Congress on Evolutionary Computation held in 2020 (CEC’2020) for optimization tests, and ten chemical data sets were applied to validate the performance of the FNNs classifier. The proposed algorithm’s results have been evaluated with those of other well-known optimization methods, including Runge Kutta optimizer’s (RUN), particle swarm optimization (PSO), grey wolf optimization (GWO), Harris hawks optimization (HHO), whale optimization algorithm (WOA), slime mould algorithm (SMA) and the standard weighted mean of vectors (INFO). In addition, some improved metaheuristic algorithms. The experimental results indicate that the proposed mINFO algorithm can improve the convergence speed and generate effective search results without increasing computational costs. In addition, it has improved the FNN’s classification efficiency.

Utilization of convolutional neural networks to analyze microscopic images for high-throughput screening of mesenchymal stem cells.

This work investigated the high-throughput classification performance of microscopic images of mesenchymal stem cells (MSCs) using a hyperspectral imaging-based separable convolutional neural network (CNN) (H-SCNN) model. Human bone marrow mesenchymal stem cells (hBMSCs) were cultured, and microscopic images were acquired using a fully automated microscope. Flow cytometry (FCT) was employed for functional classification. Subsequently, the H-SCNN model was established. The hyperspectral microscopic (HSM) images were created, and the spatial-spectral combined distance (SSCD) was employed to derive the spatial-spectral neighbors (SSNs) for each pixel in the training set to determine the optimal parameters. Then, a separable CNN (SCNN) was adopted instead of the classic convolutional layer. Additionally, cultured cells were seeded into 96-well plates, and high-functioning hBMSCs were screened using both manual visual inspection (MV group) and the H-SCNN model (H-SCNN group), with each group consisting of 96 samples. FCT served as the benchmark to compare the area under the curve (AUC), F1 score, accuracy (Acc), sensitivity (Sen), specificity (Spe), positive predictive value (PPV), and negative predictive value (NPV) between the manual and model groups. The best classification Acc was 0.862 when using window size of 9 and 12 SSNs. The classification Acc of the SCNN model, ResNet model, and VGGNet model gradually increased with the increase in sample size, reaching 89.56 ± 3.09, 80.61 ± 2.83, and 80.06 ± 3.01%, respectively at the sample size of 100. The corresponding training time for the SCNN model was significantly shorter at 21.32 ± 1.09 min compared to ResNet (36.09 ± 3.11 min) and VGGNet models (34.73 ± 3.72 min) (P < 0.05). Furthermore, the classification AUC, F1 score, Acc, Sen, Spe, PPV, and NPV were all higher in the H-SCNN group, with significantly less time required (P < 0.05). Microscopic images based on the H-SCNN model proved to be effective for the classification assessment of hBMSCs, demonstrating excellent performance in classification Acc and efficiency, enabling its potential to be a powerful tool in future MSCs research.

Supersonic coaxial aerodynamic atomization dust removal technology

The high concentration of respirable dust pollution created during coal mining has long been known to be harmful to employee health. A water absorbing atomization device has certain advantages when spray trapping particle sizes of PM2.5–10. To further improve the PM0–2.5 trapping efficiency, supersonic coaxial pneumatic atomization dust removal technology has been developed. The effects of fog droplet characteristics on the instantaneous diffusion of dust were studied by numerical simulation and macro- and microexperiments for the first time, and the coupling characteristics of fog droplets and dust fields were obtained. The results show that with increasing aerodynamic pressure, the supersonic range extends along the axis toward the nozzle outlet, and the average velocity in the tube increases. Under different pressures, the droplet particle size in the supersonic coaxial atomizing nozzle is <6 μm and decreases with increasing aerodynamic pressure. When a droplet effuses from the nozzle, the transonic distribution of the flow field causes the droplet velocity to increase first and then decrease under the drag force. The droplet field characteristic distribution of supersonic coaxial atomization is determined by droplet evaporation, condensation, and migration. Under the same pressure, with increasing spray distance, the distribution of the droplet particle size increases in a stepwise manner, and the droplet velocity decreases according to an exponential function so that the droplet field produces a high-speed fine fog area. The range of droplets with higher velocities and smaller particle sizes is mainly influenced by migration and increases with increasing pressure. The coupling effect droplet field and dust field can be characterized by the instantaneous dispersion of dust and are determined by the distribution characteristics of the fog droplet field. The large range of high-speed fine fog produced by supersonic coaxial atomization technology easily traps respirable dust, and the classification efficiency of PM0–2.5 reaches 90%. In this study, a new dynamic microfog dust trapping technique was proposed, and a new method of instantaneous sampling combined with a microscopic dispersion test was adopted to characterize the temporal and spatial distributions of dust fields affected by fog droplet fields, reveal the generation of dynamic microfog and the mechanism of dust trapping, enrich the theory of fine dust trapping, and provide technical support for the safe production and utilization of coal.

Identification of disulfidptosis- and ferroptosis-related transcripts in periodontitis by bioinformatics analysis and experimental validation.

Disulfidptosis and ferroptosis are forms of programmed cell death that may be associated with the pathogenesis of periodontitis. Our study developed periodontitis-associated biomarkers combining disulfidptosis and ferroptosis, which provides a new perspective on the pathogenesis of periodontitis. Firstly, we obtained the periodontitis dataset from public databases and found disulfidptosis- and ferroptosis-related differentially expressed transcripts based on the disulfidptosis and ferroptosis transcript sets. After that, transcripts that are tissue biomarkers for periodontitis were found using three machine learning methods. We also generated transcript subclusters from two periodontitis microarray datasets: GSE16134 and GSE23586. Furthermore, three transcripts with the best classification efficiency were further screened. Their expression and classification efficacy were validated using qRT-PCR. Finally, periodontal clinical indicators of 32 clinical patients were collected, and the correlation between three transcripts above and periodontal clinical indicators was analyzed. We identified six transcripts that are tissue biomarkers for periodontitis, the top three transcripts with the best classification, and delineated two expression patterns in periodontitis. Our study found that disulfidptosis and ferroptosis were associated with immune responses and may involve periodontitis genesis.

Improving the classification of a nanocomposite using nanoparticles based on a meta-analysis study, recurrent neural network and recurrent neural network Monte-Carlo algorithms

This paper may be the first meta-analysis that presents a comprehensive synthesis of scientific works spanning the last five years, focusing on methodologies and results related to the analysis of nanocomposite using nanoparticles. The primary objective is to identify the optimal algorithm using software information and leading to better classification methodology. Specifically, this study comes up with the advantages and the drawbacks of the most used algorithms and proposes an enhancement and performance of Recurrent Neural Networks based on Long Short Term Memory (LSTM) neurons. Besides, a comparison of Deep Learning methods for the classification of polymeric nanoparticles, with polypropylene serving as a case study will be implemented. Experiment comparisons are conducted to assess with one physical property, later expanded to four properties and finally to eight properties. Neural networks, including Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN), and Recurrent Neural Networks-Monte Carlo, are employed for simulations. The evaluation criteria encompass accuracy, calculation time, mean square error (MSE) and other metrics. The findings contribute to the selection of an optimal algorithm for the analysis of polymeric nanoparticles, emphasizing the potential of Deep Learning methodologies, particularly Recurrent Neural Networks Monte Carlo, in advancing classification accuracy and efficiency.

Comparison on Environmental Benefits of Municipal Solid Waste Management in Suzhou Before and After Classification

In order to systematically understand the urban environmental benefit improvement of municipal solid waste （MSW） classification, based on the disposal data of MSW before and after the MSW classification in Suzhou from 2017 to 2021, the environmental impact potential （EIP） of the MSW collection-transportation-disposal process was calculated, and the environmental benefits of the MSW integrated management in Suzhou to 2035 were predicted. After the MSW classification in Suzhou at the end of 2019, the EIP （in terms of PET2000, the same below） of the per unit weight of MSW was reduced by 18.38% from 2.34×10-13 t-1 in 2017 to 1.91×10-13 t-1 in 2021. The environmental benefits of the MSW integrated management could be improved by classification. Based on the Suzhou MSW removal and transportation situation in 2021, different classification and disposal scenarios were established to calculate. It was found that after the classification effect showed gradient improvement, and the disposal capacity matched accordingly, the environmental benefits of MSW were further improved. Under the planning disposal capacity scenario of "zero waste to landfill", the EIP and the total carbon emissions of per unit weight of MSW should be reduced by 23.96% and 30.73%, respectively, compared with the actual situation in 2021. Based on the linear model of population and economic development level of Suzhou, it is expected that the annual production of MSW in Suzhou will be increased to 6.965 million tons in 2035. Under the background of continuous improvement of MSW classification and continuous optimization of city appearance and environment in Suzhou, based on the status quo of terminal disposal capacity in Suzhou, the EIP of per unit weight of MSW after improving the efficiency of classification by 2035 was predicted to be 1.54×10-13 t-1, the total EIP would be 1.05×10-6, and the total carbon emissions would increase to 3.80 million tons. Under the ideal scenario of expanding the scale of waste disposal, "zero landfill" of raw MSW, and full resource utilization of food waste, the EIP of per unit weight of MSW in 2035 was predicted to be 1.28×10-13 t-1, and the total EIP and the total carbon emissions would be 8.69×10-7 and 3.23 million tons, respectively, which was approximately 5.65% and 1.23% less than the actual scenario in 2021, respectively. The EIP and carbon emissions of MSW integrated management could be controlled better by the coordinated promotion of classified collection and transportation and quality disposal.

Transformer-based decoder of melanoma classification using hand-crafted texture feature fusion and Gray Wolf Optimization algorithm

Melanoma is a type of skin cancer that poses significant health risks and requires early detection for effective treatment. This study proposing a novel approach that integrates a transformer-based model with hand-crafted texture features and Gray Wolf Optimization, aiming to enhance efficiency of melanoma classification. Preprocessing involves standardizing image dimensions and enhancing image quality through median filtering techniques. Texture features, including GLCM and LBP, are extracted to capture spatial patterns indicative of melanoma. The GWO algorithm is applied to select the most discriminative features. A transformer-based decoder is then employed for classification, leveraging attention mechanisms to capture contextual dependencies. The experimental validation on the HAM10000 dataset and ISIC2019 dataset showcases the effectiveness of the proposed methodology. The transformer-based model, integrated with hand-crafted texture features and guided by Gray Wolf Optimization, achieves outstanding results. The results showed that the proposed method performed well in melanoma detection tasks, achieving an accuracy and F1-score of 99.54% and 99.11% on the HAM10000 dataset, and an accuracy of 99.47%, and F1-score of 99.25% on the ISIC2019 dataset.• We use the concepts of LBP and GLCM to extract features from the skin lesion images.• The Gray Wolf Optimization (GWO) algorithm is employed for feature selection.• A decoder based on Transformers is utilized for melanoma classification.

Attention-Based Deep Learning Approach for Breast Cancer Histopathological Image Multi-Classification.

Breast cancer diagnosis from histopathology images is often time consuming and prone to human error, impacting treatment and prognosis. Deep learning diagnostic methods offer the potential for improved accuracy and efficiency in breast cancer detection and classification. However, they struggle with limited data and subtle variations within and between cancer types. Attention mechanisms provide feature refinement capabilities that have shown promise in overcoming such challenges. To this end, this paper proposes the Efficient Channel Spatial Attention Network (ECSAnet), an architecture built on EfficientNetV2 and augmented with a convolutional block attention module (CBAM) and additional fully connected layers. ECSAnet was fine-tuned using the BreakHis dataset, employing Reinhard stain normalization and image augmentation techniques to minimize overfitting and enhance generalizability. In testing, ECSAnet outperformed AlexNet, DenseNet121, EfficientNetV2-S, InceptionNetV3, ResNet50, and VGG16 in most settings, achieving accuracies of 94.2% at 40×, 92.96% at 100×, 88.41% at 200×, and 89.42% at 400× magnifications. The results highlight the effectiveness of CBAM in improving classification accuracy and the importance of stain normalization for generalizability.

A Hybrid Classification Model (Fruits or Vegetable) Using Deep Learning Techniques

Abstract: In modern vision and pattern recognition, complex tasks such as picture analysis, facial recognition, fingerprint identification, and DNA sequencing necessitate a nuanced approach, often requiring the integration of multiple feature descriptors. This research proposes a multi-model identification and classification strategy leveraging multi- feature fusion techniques to address these intricate challenges. Specifically, the focus is on fruit and vegetable recognition and classification, a burgeoning field in computer and machine vision. By employing an identification system tailored to fruits and vegetables and harnessing the capabilities of MobileNetV2 architecture, customers and buyers can more easily discern the type and quality of produce. MobileNetV2, a convolutional neural network architecture optimized for mobile devices, offers promising performance in real-world applications. This abstract highlight the significance of CNNs and MobileNetV2 in tackling multifaceted recognition tasks, underscoring the potential for enhanced efficiency and accuracy in fruit and vegetable classification.

Leukemia Detection using Machine Learning Algorithms: Current trends and future directions

The process of medical diagnosis of leukemia cases is a complex process and requires diligent efforts. It is done by examining samples under a microscope and distinguishing the number, shape, size, and morphological features of white blood cells. This process takes a long time to predict leukemia. The professional skills and experience of the pathologist may also influence this procedure as a large number of overlapping structures and conditions, distractions, fatigue, and limitations in the human visual system can lead to an inappropriate diagnosis. Machine and deep learning approaches have been found to be effective strategies for enhancing the precision and efficiency of diagnosis and classification of medical images, including those of microscopic blood cells. In this paper, we will review the recent studies of leukemia detection and/or classification in the period of (2015 - 2023) in machine and deep learning and the combining of them. The review of these schemes is carried out in a systematic manner. In order to achieve the desired objective, segmentation schemes can be classified into four main categories: supervised machine learning techniques, unsupervised machine learning techniques, deep learning approaches, and traditional image processing techniques. Classification approaches can be categorized into three main groups: classical machine learning, deep learning, and a combination of both. CNN-based categorization systems can be further classified into three categories: conventional CNN, transfer learning, and additional developments in CNN. This paper also provides a concise analysis of these strategies and their significance in the categorization of leukemia. Ultimately, a comprehensive examination is conducted to elucidate the current state of research in this particular domain.

Leukemia Detection using Machine Learning Algorithms: Current trends and future directions

The process of medical diagnosis of leukemia cases is a complex process and requires diligent efforts. It is done by examining samples under a microscope and distinguishing the number, shape, size, and morphological features of white blood cells. This process takes a long time to predict leukemia. The professional skills and experience of the pathologist may also influence this procedure as a large number of overlapping structures and conditions, distractions, fatigue, and limitations in the human visual system can lead to an inappropriate diagnosis. Machine and deep learning approaches have been found to be effective strategies for enhancing the precision and efficiency of diagnosis and classification of medical images, including those of microscopic blood cells. In this paper, we will review the recent studies of leukemia detection and/or classification in the period of (2015 - 2023) in machine and deep learning and the combining of them. The review of these schemes is carried out in a systematic manner. In order to achieve the desired objective, segmentation schemes can be classified into four main categories: supervised machine learning techniques, unsupervised machine learning techniques, deep learning approaches, and traditional image processing techniques. Classification approaches can be categorized into three main groups: classical machine learning, deep learning, and a combination of both. CNN-based categorization systems can be further classified into three categories: conventional CNN, transfer learning, and additional developments in CNN. This paper also provides a concise analysis of these strategies and their significance in the categorization of leukemia. Ultimately, a comprehensive examination is conducted to elucidate the current state of research in this particular domain.

Effect of Hyperparameter Tuning on the Performance of YOLOv8 for Multi Crop Classification on UAV Images

This study investigates the performance of YOLOv8, a Convolutional Neural Network (CNN) architecture, for multi-crop classification in a mixed farm with Unmanned Aerial Vehicle (UAV) imageries. Emphasizing hyperparameter optimization, specifically batch size, the study’s primary objective is to refine the model’s batch size for improved accuracy and efficiency in crop detection and classification. Using the Google Colaboratory platform, the YOLOv8 model was trained over various batch sizes (10, 20, 30, 40, 50, 60, 70, 80, and 90) to automatically identify the five different classes (sugarcane, banana trees, spinach, pepper, and weeds) present on the UAV images. The performance of the model was assessed using classification accuracy, precision, and recall with the aim of identifying the optimal batch size. The results indicate a substantial improvement in classifier performance from batch sizes of 10 up to 60, while significant dips and peaks were recorded at batch sizes 70 to 90. Based on the analysis of the obtained results, Batch size 60 emerged with the best overall performance for automatic crop detection and classification. Although the F1 score was moderate, the combination of high accuracy, precision, and recall makes it the most balanced option. However, Batch Size 80 also shows very high precision (98%) and balanced recall (84%), which is suitable if the primary focus is on achieving high precision. The findings demonstrate the robustness of YOLOv8 for automatic crop identification and classification in a mixed crop farm while highlighting the significant impact of tuning to the appropriate batch size on the model’s overall performance.

Enhancing radiographic image interpretation: WARES-PRS model for knee bone tumour detection

ABSTRACT The early diagnosis of tumour is significant in biomedical research field to lower the severity level and restrict the process extension from cancer. Moreover, the detection of early sign of cancer is undertaken with extensive research efforts that dedicated to the disclosure and recognition of tumours. However, the limited data size as well as diverse appearance of images lowered the detection performance and failed to detect complex stage of tumour. So to solve these issues, a Weighted Adaptive Random Ensemble Support Vector-based Partial Reinforcement Search (WARES-PRS) algorithm is proposed that detected bone lesions accurately and also predicted the severity level stage efficiently. Further, the detection is performed with varied stages to diminish the presence of noise and undertaken effective classification. The performance is validated with CNUH dataset that enhanced image pre-processing tasks. Despite the proposed method uncover the mutual relationships between each pixel’s local texture and the overall image’s global context. The detection and classification efficiency is validated with various measures and the experimental results revealed that the detection accuracy is enhanced for the proposed approach by 98.5%. The outcomes of our study have exhibited a substantial contribution to assisting physicians in the detection of knee bone tumours.

Comparison of Efficiency for Imbalanced Data Classification via Simulation

Comparison of Efficiency for Imbalanced Data Classification via Simulation