Improve Classification Performance Research Articles

EEG channel and feature investigation in binary and multiple motor imagery task predictions

IntroductionMotor Imagery (MI) Electroencephalography (EEG) signals are non-stationary and dynamic physiological signals which have low signal-to-noise ratio. Hence, it is difficult to achieve high classification accuracy. Although various machine learning methods have already proven useful to that effect, the use of many features and ineffective EEG channels often leads to a complex structure of classifier algorithms. State-of-the-art studies were interested in improving classification performance with complex feature extraction and classification methods by neglecting detailed EEG channel and feature investigation in predicting MI tasks from EEGs. Here, we investigate the effects of the statistically significant feature selection method on four different feature domains (time-domain, frequency-domain, time-frequency domain, and non-linear domain) and their two different combinations to reduce the number of features and classify MI-EEG features by comparing low-dimensional matrices with well-known machine learning algorithms.MethodsOur main goal is not to find the best classifier performance but to perform feature and channel investigation in MI task classification. Therefore, the detailed investigation of the effect of EEG channels and features is implemented using a statistically significant feature distribution on 22 EEG channels for each feature set separately. We used the BCI Competition IV Dataset IIa and 288 samples per person. A total of 1,364 MI-EEG features were analyzed in this study. We tested nine distinct classifiers: Decision tree, Discriminant analysis, Logistic regression, Naive Bayes, Support vector machine, k-Nearest neighbor, Ensemble learning, Neural networks, and Kernel approximation.ResultsAmong all feature sets considered, classifications performed with non-linear and combined feature sets resulted in a maximum accuracy of 63.04% and 47.36% for binary and multiple MI task predictions, respectively. The ensemble learning classifier achieved the maximum accuracy in almost all feature sets for binary and multiple MI task classifications.DiscussionOur research thus shows that the statistically significant feature-based feature selection method significantly improves the classification performance with fewer features in almost all feature sets, enabling detailed and effective EEG channel and feature investigation.

Comparative Analysis of Conventional CNN v’s ImageNet Pretrained ResNet in Medical Image Classification

Convolutional Neural Networks (CNNs) are the prevalent technology in computer vision and have become increasingly popular for medical imaging data classification and analysis. In this field, due to the scarcity of medical data, pretrained ResNets on ImageNet can be considered a suitable first approach. This paper examines the medical imaging classification accuracy of conventional basic custom CNNs compared to ImageNet pretrained ResNets on various medical datasets in an effort to give more information about the importance of medical data and its preprocessing techniques for disease studies. Microscope-extracted cytological images were examined along with chest X-rays, MRI brain scans, and melanoma photographs. The medical images were examined in various sets, class combinations, and resolutions. Augmented image datasets and asymmetrical training and validation splits among the classes were also examined. Models were developed after they were tested and fine-tuned with respect to their network size, parameter values and network methods, image resolution, size of dataset, multitude, and genre of class. Overfitting was also examined, and comparative studies regarding the computational cost of different models were performed. The models achieved high accuracy in image classification that varies depending on the dataset and can be easily incorporated in future over-the-internet medical decision-supporting (telemedicine) environments. In addition, it appeared that conventional basic custom CNN overperformed ImageNet pretrained ResNets. The obtained results indicate the importance of utilizing medical image data as a testbed for improvements in CNN classification performance and the possibility of using CNNs and data preprocessing techniques for disease studies.

A text classification method combining in-domain pre-training and prompt learning for the steel e-commerce industry

Purpose With the development of Web information systems, steel e-commerce platforms have accumulated a large number of quality objection texts. These texts reflect consumer dissatisfaction with the dimensions, appearance and performance of steel products, providing valuable insights for product improvement and consumer decision-making. Currently, mainstream solutions rely on pre-trained models, but their performance on domain-specific data sets and few-shot data sets is not satisfactory. This paper aims to address these challenges by proposing more effective methods for improving model performance on these specialized data sets. Design/methodology/approach This paper presents a method on the basis of in-domain pre-training, bidirectional encoder representation from Transformers (BERT) and prompt learning. Specifically, a domain-specific unsupervised data set is introduced into the BERT model for in-domain pre-training, enabling the model to better understand specific language patterns in the steel e-commerce industry, enhancing the model’s generalization capability; the incorporation of prompt learning into the BERT model enhances attention to sentence context, improving classification performance on few-shot data sets. Findings Through experimental evaluation, this method demonstrates superior performance on the quality objection data set, achieving a Macro-F1 score of 93.32%. Additionally, ablation experiments further validate the significant advantages of in-domain pre-training and prompt learning in enhancing model performance. Originality/value This study clearly demonstrates the value of the new method in improving the classification of quality objection texts for steel products. The findings of this study offer practical insights for product improvement in the steel industry and provide new directions for future research on few-shot learning and domain-specific models, with potential applications in other fields.

Spontaneous transfer of relational category structures between category learning tasks: A novel approach to measure analogical transfer.

The ability to spontaneously access knowledge of relational concepts acquired in one domain and apply it to a novel domain has traditionally been explored in the analogy literature via the problem-solving paradigm. In the present work, we propose a novel procedure based on categorisation as a complementary approach to assess spontaneous analogical transfer-using one category learning task to enhance learning of the same underlying category structures in another domain. In Experiment 1, we demonstrate larger improvements in classification performance across blocks of training in a target category learning task among participants that underwent a base category learning task relative to a separate group of participants learning the target category structures for the first time, thus providing evidence for spontaneous transfer of the category structures. In Experiment 2, we demonstrate similar evidence of spontaneous transfer for participants that underwent a comparison-based base category learning task under a more rigorous context shift between the base and target category learning tasks. Additional exploratory analyses across both experiments showcase ways in which this paradigm can be used to answer questions regarding the analogical transfer of relational category structures and generate promising paths for future work.

Fuzzy logic and machine learning for diabetes risk prediction using modifiable factors

Diabetes mellitus, a global health concern, includes type 1 diabetes, with an uncontrollable risk, and type 2 diabetes, where risk can be managed through lifestyle modifications. This study examines the impact of modifiable risk factors—diet, physical activity, and body mass index (BMI)—on type 2 diabetes development. Using fuzzy logic, binary variables from a healthcare diabetes dataset were transformed into a fuzzy format, generating three output classes: "no diabetes risk," "possible diabetes risk," and "diabetes risk present." The intermediate class, "possible diabetes risk," serves as an alert for adopting healthier lifestyles to mitigate risk. Machine learning was applied to both the original and fuzzy-transformed datasets. While the original dataset provided binary outputs with moderate accuracy and higher computation times, the fuzzy-transformed dataset yielded more nuanced predictions, reduced computation time, and improved classifier performance. This approach enhances diabetes risk assessment and supports proactive interventions.

A Generalized Attention Mechanism to Enhance the Accuracy Performance of Neural Networks.

In many modern machine learning (ML) models, attention mechanisms (AMs) play a crucial role in processing data and identifying significant parts of the inputs, whether these are text or images. This selective focus enables subsequent stages of the model to achieve improved classification performance. Traditionally, AMs are applied as a preprocessing substructure before a neural network, such as in encoder/decoder architectures. In this paper, we extend the application of AMs to intermediate stages of data propagation within ML models. Specifically, we propose a generalized attention mechanism (GAM), which can be integrated before each layer of a neural network for classification tasks. The proposed GAM allows for at each layer/step of the ML architecture identification of the most relevant sections of the intermediate results. Our experimental results demonstrate that incorporating the proposed GAM into various ML models consistently enhances the accuracy of these models. This improvement is achieved with only a marginal increase in the number of parameters, which does not significantly affect the training time.

Plant disease classification using novel integration of deep learning CNN and graph convolutional networks

Plant diseases present substantial challenges to global agriculture, significantly affecting crop yields and jeopardizing food security. Accurate and timely detection of these diseases is paramount for mitigating their adverse effects. This paper proposes a novel approach for plant disease classification by integrating convolutional neural networks (CNNs) and graph convolutional networks (GCNs). The model aims to enhance classification accuracy by leveraging both visual features extracted by CNNs and relational information captured by GCNs. Using a Kaggle dataset containing images of diseased and healthy plant leaves from 31 classes, including apple, corn, grape, peach, pepper bell, potato, strawberry, and tomato. Standalone CNN models were trained on image data from each plant type, while standalone GCN models utilized graph-structured data representing plant relationships within each subset. The proposed integrated CNN-GCN model capitalizes on the complementary strengths of CNNs and GCNs to achieve improved classification performance. Through rigorous experimentation and comparative analysis, the effectiveness of the integrated CNN-GCN approach was evaluated alongside standalone CNN and GCN models across all plant types. Results demonstrated the superiority of the integrated model, highlighting its potential for enhancing plant disease classification accuracy.

Classification of Skin Diseases using Decision Tree Algorithm on an Imbalanced Dataset

Skin infections caused by pathogens such as bacteria and fungi are common and can lead to serious health complications if not properly managed. Accurate classification of these infections is crucial for effective treatment and management. This study focuses on classifying two skin diseases, Chickenpox and Shingles, using a Decision Tree algorithm applied to an imbalanced dataset sourced from Kaggle. The dataset, which is imbalanced by nature, was split into training (80%) and testing (20%) subsets. Pre-processing involved segmentation using Thresholding to isolate regions of interest and feature extraction using Hu Moments to capture shape characteristics of the lesions. The dataset was scaled to ensure that all features had a mean of 0 and variance of 1. The classifier's performance was evaluated using 5-fold cross-validation, yielding a mean accuracy of 66.06%, with precision, recall, and F1-scores indicating moderate performance. The study highlights the challenges posed by imbalanced datasets and the limitations of the Decision Tree algorithm in this context. The results underscore the importance of proper pre-processing and feature extraction but also suggest the need for more advanced classification techniques and data balancing methods. This research contributes to the field by providing a detailed methodology and comprehensive evaluation metrics, offering insights into the application of machine learning for medical image classification. Future work should focus on improving classifier performance through data augmentation, advanced feature extraction, and exploring other machine learning models better suited for imbalanced datasets.

Speech Signal Analysis in Patients with Parkinson’s Disease, Taking into Account Phonation, Articulation, and Prosody of Speech

This study involved performing tests to detect Parkinson’s disease (PD) based on voice changes, including speech phonation, articulation, and prosody, in patients with PD using different types of speech signal. For this purpose, during the first stage of the investigation, three separately modeled PD diagnosis systems using different types of speech signal characteristics were defined. The classification results were obtained when the SVM method was applied compared to the k-nearest neighbors method applying 1-nn in general. The tests were carried out within the database of patient voice recordings collected in the Department of Neurology at the Medical University of Warsaw. The second stage of the research was the selection of descriptors. The SFFS (sequential floating forward) method was applied together with the k-nn and SVM classifier. These subsets were used to create a new system based on a descriptor loose integration. Within the experiments conducted, general diagnosis results lead to improved classifier performance only in certain cases. This prompted the authors to conduct the last experimental research stage—selection at the feature fusion stage. Feature evaluation ranking methods (Relief, Fisher Score, F-tests, Chi-square) were applied for this purpose. With 10-fold validation, the k-nn method achieved an recognition rate of 92.2% with 91.1% sensitivity and 93.3% specificity.

Domain-Invariant Few-Shot Contrastive Learning for Hyperspectral Image Classification

In Hyperspectral Image (HSI) classification, acquiring large quantities of high-quality labeled samples is typically costly and impractical. Traditional deep learning methods are limited in such scenarios due to their dependence on sample quantities. To address this challenge, researchers have turned to Few-Shot Learning (FSL). Although existing FSL methods improve classification performance by enhancing domain invariance through domain adaptation, they often overlook the critical issue of high inter-class similarity and large intra-class variability. Moreover, during domain alignment, features of different categories within the same domain may become confused. To address these issues, this paper proposes a novel Domain-Invariant Few-Shot Contrastive Learning (DIFSCL) method, which combines domain adaptation and contrastive learning strategies to not only learn domain-invariant features but also significantly enhance inter-class discriminability. Based on this, we further design a multi-scale adaptive attention mechanism for a hyperspectral feature extraction network to more effectively extract and optimize generalized features within the DIFSCL framework, significantly improving intra-class consistency and inter-class discriminative capability of features. Experimental results on three widely used HSI datasets demonstrate that our method significantly outperforms existing techniques in few-shot classification tasks.

Surfing beta burst waveforms to improve motor imagery-based BCI

Abstract Our understanding of motor-related, macroscale brain processes has been significantly shaped by the description of the event-related desynchronization (ERD) and synchronization (ERS) phenomena in the mu and beta frequency bands prior to, during and following movement. The demonstration of reproducible, spatially- and band-limited signal power changes has, consequently, attracted the interest of non invasive brain-computer interface (BCI) research for a long time. BCIs often rely on motor imagery (MI) experimental paradigms that are expected to generate brain signal modulations analogous to movement-related ERD and ERS. However, a number of recent neuroscience studies has questioned the nature of these phenomena. Beta band activity has been shown to occur, on a single-trial level, in short, transient and heterogeneous events termed bursts rather than sustained oscillations. In a previous study, we established that an analysis of hand MI binary classification tasks based on beta bursts can be superior to beta power in terms of classification score. In this article we elaborate on this idea, proposing a signal processing algorithm that is comparable to- and compatible with state-of-the-art techniques. Our pipeline filters brain recordings by convolving them with kernels extracted from beta bursts and then applies spatial filtering before classification. This data-driven filtering allowed for a simple and efficient analysis of signals from multiple sensors thus being suitable for online applications. By adopting a time-resolved decoding approach we explored MI dynamics and showed the specificity of the new classification features. In accordance with previous results, beta bursts improved classification performance compared to beta band power, while often increasing information transfer rate compared to state-of-the-art approaches.

A Study on Text Classification in the Age of Large Language Models

A Study on Text Classification in the Age of Large Language Models

Automated Generation of Lung Cytological Images from Image Findings Using Text-to-Image Technology

Cytology, a type of pathological examination, involves sampling cells from the human body and observing the morphology of the nucleus, cytoplasm, and cell arrangement. In developing classification AI technologies to support cytology, it is essential to collect and utilize a diverse range of images without bias. However, this is often challenging in practice because of the epidemiologic bias of cancer types and cellular characteristics. The main aim of this study was to develop a method to generate cytological diagnostic images from image findings using text-to-image technology in order to generate diverse images. In the proposed method, we collected Papanicolaou-stained specimens derived from the lung cells of 135 lung cancer patients, from which we extracted 472 patch images. Descriptions of the corresponding findings for these patch images were compiled to create a data set. This dataset was then utilized to finetune the Stable Diffusion (SD) v1 and v2 models. The cell images generated by this method closely resemble real images, and both cytotechnologists and cytopathologists provided positive subjective evaluations. Furthermore, SDv2 demonstrated shapes and contours of nuclei and cytoplasm that were more similar to real images compared to SDv1, showing superior performance in quantitative evaluation metrics. When the generated images were utilized in the classification tasks for cytological images, there was an improvement in classification performance. These results indicate that the proposed method may be effective for generating high-quality cytological images, which enables the image classification model to learn diverse features, thereby improving classification performance.

Evaluating the Performance of Vascular Feature Extraction Boosting Algorithm for Peripheral Arterial Disease Detection

A common vascular disease called peripheral arterial disease (PAD) is characterized by constricted or blocked arteries in the legs, which lowers blood flow and raises the risk of consequences including cardiovascular events or amputation of a limb. Timely intervention and management of PAD are contingent upon early identification. Atherosclerosis, or plaque accumulation in the arteries, is the main cause of this illness. Therefore, leg pain, cramping, numbness, weakness, or coolness in the legs are possible signs of PAD, especially when engaging in physical activity. In addition to impairing mobility and quality of life, PAD raises the possibility of consequences like tissue damage, persistent sores, and even limb amputation if treatment is not received. Mixes of dietary adjustments, medication, and, in extreme situations, surgical procedures are used to manage PAD. A nutritious diet, frequent exercise, giving up smoking, and keeping a healthy weight are a few examples of lifestyle changes. It may be necessary to prescribe pharmaceuticals to decrease cholesterol, antiplatelet agents, blood flow improvers, and symptom managers. Procedures like angioplasty, stenting, or bypass surgery may be required in cases when PAD progresses and symptoms are severe to restore blood flow to the affected limbs. To avoid issues and enhance results, PAD must be identified early and managed effectively. As a result, those who are at risk such as those with diabetes, high blood pressure, high cholesterol, or a history of smoking should have screening for PAD regularly. All things considered, PAD is a dangerous illness that needs to be managed proactively to avoid complications and preserve a high standard of living. Through the management of risk factors, adoption of a healthy lifestyle, and adherence to an individualized treatment plan, people with PAD can effectively manage their illness and lower their chance of complications. For long-term treatment and best results, regular monitoring and follow-up with healthcare specialists are necessary. Vascular feature extraction boosting (VFEB), a hybrid algorithm that combines the strength of vascular feature extraction with boosting approaches, is the unique strategy for PAD identification that is present in this study. The VFEB approach makes use of gradient boosting machines (GBMs) to improve classification performance based on these features and convolutional neural networks (CNNs) to extract discriminative features from vascular imaging data. The goal of VFEB is to increase the precision and resilience of PAD detection by combining CNNs for feature extraction with GBMs for classification. Using a dataset of vascular imaging data, we assess the VFEB algorithm’s performance and compare it with other established techniques. The findings show that VFEB performs better than other methods at identifying PAD, providing encouraging opportunities for the early detection and treatment of this crippling vascular ailment. The VFEB system achieves an outstanding accuracy of 99.87%, an F1 Score of 99.64, and MCC 99%. Compared to the conventional methods, VFEB obtains improved accuracy, F1 Score, and MCC by integrating boosting techniques with vascular feature extraction. This study emphasizes the value of utilizing cutting-edge computational tools to improve vascular health outcomes and shows how hybrid algorithms, such as VFEB, may improve PAD identification.

MAPM:PolSAR Image Classification with Masked Autoencoder Based on Position Prediction and Memory Tokens

Deep learning methods have shown significant advantages in polarimetric synthetic aperture radar (PolSAR) image classification. However, their performances rely on a large number of labeled data. To alleviate this problem, this paper proposes a PolSAR image classification method with a Masked Autoencoder based on Position prediction and Memory tokens (MAPM). First, MAPM designs a Masked Autoencoder (MAE) based on the transformer for pre-training, which can boost feature learning and improve classification results based on the number of labeled samples. Secondly, since the transformer is relatively insensitive to the order of the input tokens, a position prediction strategy is introduced in the encoder part of the MAE. It can effectively capture subtle differences and discriminate complex, blurry boundaries in PolSAR images. In the fine-tuning stage, the addition of learnable memory tokens can improve classification performance. In addition, L1 loss is used for MAE optimization to enhance the robustness of the model to outliers in PolSAR data. Experimental results show the effectiveness and advantages of the proposed MAPM in PolSAR image classification. Specifically, MAPM achieves performance gains of about 1% in classification accuracy compared with existing methods.

Predicting Operational Events in Mechanized Weed Control Operations by Offline Multi-Modal Data and Machine Learning Provides Highly Accurate Classification in Time Domain

Monitoring of operations has become a critical activity in forestry, aiming to provide the data required by planning and production management. Conventional methods, on the other hand, come at a high expense of resources. A neural network was trained, validated, and tested in this study based on multi-modal data to classify relevant operational events in mechanized weed control operations. The architecture of a neural network was tuned in terms of the number of hidden layers and neurons, and the regularization term was set at various values to obtain optimally tuned models for three data modalities: triaxial acceleration data coupled with speed extracted from GNSS signals (AS), triaxial acceleration (A), and speed alone (S). In the training and validation phase, the models based on AS and A achieved a very high classification accuracy, accounting for 92 to 93% when considering four relevant events. In the testing phase, which was run on unseen data, the classification accuracy reached figures of 91 to 92%, indicating a good generalization ability of the models. The results point out that multimodal data are able to provide the features for distinguishing events and add spatial context to the monitored operations, standing as a suitable solution for offline, partly automated monitoring. Future studies are required to see how the capabilities of online, real-time technologies such as deep learning coupled with computer vision can add more context and improve classification performance.

Recognition of Sheep Feeding Behavior in Sheepfolds Using Fusion Spectrogram Depth Features and Acoustic Features.

In precision feeding, non-contact and pressure-free monitoring of sheep feeding behavior is crucial for health monitoring and optimizing production management. The experimental conditions and real-world environments differ when using acoustic sensors to identify sheep feeding behaviors, leading to discrepancies and consequently posing challenges for achieving high-accuracy classification in complex production environments. This study enhances the classification performance by integrating the deep spectrogram features and acoustic characteristics associated with feeding behavior. We conducted the task of collecting sound data in actual production environments, considering noise and complex surroundings. The method included evaluating and filtering the optimal acoustic features, utilizing a customized convolutional neural network (SheepVGG-Lite) to extract Short-Time Fourier Transform (STFT) spectrograms and Constant Q Transform (CQT) spectrograms' deep features, employing cross-spectrogram feature fusion and assessing classification performance through a support vector machine (SVM). Results indicate that the fusion of cross-spectral features significantly improved classification performance, achieving a classification accuracy of 96.47%. These findings highlight the value of integrating acoustic features with spectrogram deep features for accurately recognizing sheep feeding behavior.

Machine Learning‐Based Wind Classification by Wing Deformation in Biomimetic Flapping Robots: Biomimetic Flexible Structures Improve Wind Sensing

Flying animals such as insects and birds have strain receptors on their wings. The functions and information processing capabilities of these strain receptors, however, are largely unknown. Herein, the potential ability of wing strain sensors to detect wind direction in flapping flight is experimentally explored. Seven strain gauges are attached to the biomimetic wing shafts of flexible wings. The wings flap through an electric mechanism emulating hovering flight in a wind tunnel with gentle wind, and a convolutional neural network model for wind direction classification is developed. The results show that with only one strain gauge, accurate wind classification is achieved using segmented data of ≈1 flapping cycle. Even with segmented data of only 0.2 flapping cycles, wind classification can be achieved with all seven strain gauges. Moreover, the use of wing shafts improves the classification accuracy, especially with shorter segmented data. Additional flapping phase information does not substantially improve classification performance. These results suggest that hovering animals determine the wind direction via strain sensing, which is useful for flight control. The implementation of wing strain sensors in flapping‐wing aerial robots may improve flight control ability.

Enhancing Skin Lesion Classification Performance with the ABC Ensemble Model

Skin cancer is one of the most easily developed cancers and is continuously seeing an increased incidence rate. In this study, we propose a novel ABC ensemble model for skin lesion classification by leveraging the ABCD rule, which is commonly used in dermatology to evaluate lesion features such as asymmetry, border, color, and diameter. Our model consists of five distinct blocks, two of which focus on learning general image characteristics, while the remaining three focus on specialized features related to the ABCD rule. The final classification results are achieved through a weighted soft voting approach, where the generalization blocks are assigned higher weights to optimize performance. Through 15 experiments using various model configurations, we show that the weighted ABC ensemble model outperforms the baseline models, achieving the best performance with an accuracy of 0.9326 and an F1-score of 0.9302. Additionally, Grad-CAM analysis is employed to assess how each block in the ensemble focuses on distinct lesion features, further enhancing the interpretability and reliability of the model. Our findings demonstrate that integrating general image features with specific lesion characteristics improves classification performance, and that adjusting the soft voting weights yields optimal results. This novel model offers a reliable tool for early skin lesion diagnosis.

Enhancing Image Classification with Super-Resolution Techniques: A Comparative Study of SRResNet and SRGAN

Abstract. This paper explores the use of super-resolution (SR) approaches to enhance the performance of image classification, with particular attention to the effects of various SR models on classification accuracy. Using the ImageNet Dogs dataset for assessment, the paper examines two SR techniques: Super Resolution Generative Adversarial Networks (SRGAN) and Super Resolution Residual Networks (SRResNet). The research demonstrates that deep learning-based SR methods can enhance classification accuracy. Notably, SRResNet is identified as the superior method for improving classification performance, despite generating less visually appealing images compared to SRGAN. These finding highlights that while Generative Adversarial Networks (GANs) and perceptual loss functions can enhance image quality, their impact on classification accuracy may not always be substantial. The study offers important new perspectives on the relative merits of different SR approaches, highlighting the necessity of choosing the right SR methods in accordance with the particular demands of picture classification tasks. The results suggest that SRResNet, with its focus on accuracy over visual appeal, is more effective for boosting classification model performance, offering guidance for optimizing SR methods in practical image classification applications.