Improve Classification Accuracy Research Articles

Enhancing Medical Signal Processing and Diagnosis with AI-Generated Content Techniques.

In medical diagnostics, the accurate classification and analysis of biomedical signals play a crucial role, particularly in the diagnosis of neurological disorders such as epilepsy. Electroencephalogram (EEG) signals, which represent the electrical activity of the brain, are fundamental in identifying epileptic seizures. However, challenges such as data scarcity and imbalance significantly hinder the development of robust diagnostic models. Addressing these challenges, in this paper, we explore enhancing medical signal processing and diagnosis, with a focus on epilepsy classification through EEG signals, by harnessing AI-generated content techniques. We introduce a novel framework that utilizes generative adversarial networks for the generation of synthetic EEG signals to augment existing datasets, thereby mitigating issues of data scarcity and imbalance. Furthermore, we incorporate an attention-based temporal convolutional network model to efficiently process and classify EEG signals by emphasizing salient features crucial for accurate diagnosis. Our comprehensive evaluation, including rigorous ablation studies, is conducted on the widely recognized Bonn Epilepsy Data. The results achieves an accuracy of 98.89% and F1 score of 98.91%. The findings demonstrate substantial improvements in epilepsy classification accuracy, showcasing the potential of AI-generated content in advancing the field of medical signal processing and diagnosis.

Modified receiver architecture in software-defined radio for real-time modulation classification

Automatic modulation classification (AMC) is an important process for future communication systems with prominent applications from spectrum management, and secure communication, to cognitive radio. The requirement for an efficient AMC classifier is due to its capability in blind modulation recognition, which is a difficult task in real scenarios where the limitations of traditional hardware and the complexity of channel impairments are involved. Therefore, this paper proposes a complete real-time AMC system based on software-defined radio and deep learning architecture. The system demodulation performance is verified through simulations and real channel impairment conditions to ensure reliability. With at most 6 times reduced number of parameters, two proposed models convolutional long short-term memory deep neural network and residual long short-term memory neural network also show a general improvement in classification accuracy compared with reference studies. The performance of these models at real-time AMC is tested with suitable processing time for practical applications.

Classification of osteoarthritic and healthy cartilage using deep learning with Raman spectra

Raman spectroscopy is a rapid method for analysing the molecular composition of biological material. However, noise contamination in the spectral data necessitates careful pre-processing prior to analysis. Here we propose an end-to-end Convolutional Neural Network to automatically learn an optimal combination of pre-processing strategies, for the classification of Raman spectra of superficial and deep layers of cartilage harvested from 45 Osteoarthritis and 19 Osteoporosis (Healthy controls) patients. Using 6-fold cross-validation, the Multi-Convolutional Neural Network achieves comparable or improved classification accuracy against the best-performing Convolutional Neural Network applied to either the raw or pre-processed spectra. We utilised Integrated Gradients to identify the contributing features (Raman signatures) in the network decision process, showing they are biologically relevant. Using these features, we compared Artificial Neural Networks, Decision Trees and Support Vector Machines for the feature selection task. Results show that training on fewer than 3 and 300 features, respectively, for the disease classification and layer assignment task provide performance comparable to the best-performing CNN-based network applied to the full dataset. Our approach, incorporating multi-channel input and Integrated Gradients, can potentially facilitate the clinical translation of Raman spectroscopy-based diagnosis without the need for laborious manual pre-processing and feature selection.

Classification of osteoarthritic and healthy cartilage using deep learning with Raman spectra

Raman spectroscopy is a rapid method for analysing the molecular composition of biological material. However, noise contamination in the spectral data necessitates careful pre-processing prior to analysis. Here we propose an end-to-end Convolutional Neural Network to automatically learn an optimal combination of pre-processing strategies, for the classification of Raman spectra of superficial and deep layers of cartilage harvested from 45 Osteoarthritis and 19 Osteoporosis (Healthy controls) patients. Using 6-fold cross-validation, the Multi-Convolutional Neural Network achieves comparable or improved classification accuracy against the best-performing Convolutional Neural Network applied to either the raw or pre-processed spectra. We utilised Integrated Gradients to identify the contributing features (Raman signatures) in the network decision process, showing they are biologically relevant. Using these features, we compared Artificial Neural Networks, Decision Trees and Support Vector Machines for the feature selection task. Results show that training on fewer than 3 and 300 features, respectively, for the disease classification and layer assignment task provide performance comparable to the best-performing CNN-based network applied to the full dataset. Our approach, incorporating multi-channel input and Integrated Gradients, can potentially facilitate the clinical translation of Raman spectroscopy-based diagnosis without the need for laborious manual pre-processing and feature selection.

Highly Efficient Back-End-of-Line Compatible Flexible Si-Based Optical Memristive Crossbar Array for Edge Neuromorphic Physiological Signal Processing and Bionic Machine Vision

HighlightsA novel optoelectronic synapse compatible with existing chip technology is demonstrated. This device excels in mimicking memory and learning functions using light, making it ideal for future neuromorphic computing in biomedicine.Our design surpasses previous models with its ability to switch between short-term and long-term memory states using light pulses.Experiments on real-world biomedical data (electroencephalogram, electromyography, electrocardiogram) showed significant improvement in classification accuracy. This highlights the device's potential for advanced physiological signal processing and wearable health monitoring systems.

A real-time CNN–BiLSTM-based classifier for patient-centered AR-SSVEP active rehabilitation exoskeleton system

The rehabilitation of stroke has brought a serious social burden to many countries. The augmented reality steady-state visually evoked potential (AR-SSVEP) exoskeleton rehabilitation system can effectively help stroke patients recover motor function and reduce the burden on society and rehabilitation physicians. However, the decoding accuracy and efficiency of AR-SSVEP in short time stimulus are low, and the types of trajectory decoded are few. It has a negative impact on the patient’s rehabilitation interest and efficiency. In this article, a patient-centered AR-SSVEP active rehabilitation exoskeleton system is developed based on the CNN–BiLSTM fast classification algorithm. The algorithm uses CNN architecture to improve model generalization, and uses BiLSTM to improve classification accuracy. The patient-centered interactive trajectory decoding logic based on a task-driven strategy is proposed to achieve patient-defined coordinated movement trajectory of the left and right upper limb shoulder elbow joints through the 6-class brain–computer interface (BCI). The offline and online experiments were conducted on the system. In offline experiments, under a 0.5 s time window, the classification accuracy rate was 98.5%, and the information transfer rate (ITR) reached 210 bits/min. In online experiment, the patient controlled the exoskeleton of the upper limb to perform four non-repetitive trajectories, with an average time of 319 s, which was 20% more than the standard reference time. The experimental results have shown the system can effectively improve the accuracy and efficiency of motion intention identification within short time stimulus, and decode patient-defined motion trajectory. In conclusion, this study will provide a new rehabilitation way for stroke patients.

Deep Learning for Skin Cancer Classification: A Comparative Study of CNN and Vgg16 on HAM10000 Dataset

Skin cancer is one of the most dangerous types of cancer among the cancers. The early detection of skin cancer helps resolve it. Hence, it is necessary to diagnose the disease as early as possible. This paper presents Convolutional Neural Networks and the Vgg16 algorithm to recognize skin cancer types. The HAM10000 dataset, which comprises seven distinct forms of skin cancer, melanocytic nevi (nv), Melanoma (mel), basal cell carcinoma (bcc), actinic keratoses (akiec), vascular lesions (vasc), and dermatofibroma (df). This system aims to improve classification accuracy; the methodology necessitates extensive dataset preparation, including scaling, normalization, and augmentation. The Vgg16 algorithm, when combined with the CNN architecture, offers a robust basis for the classification of skin cancer. Comprehensive details on regularization techniques, optimization strategies, and training parameters are included to ensure openness and reproducibility. The system's performance is evaluated using accuracy, precision, recall, and F1-score for every type of skin cancer. This paper highlights the usefulness of the proposed method in skin cancer diagnosis and looks at challenges, constraints, and prospects for further research. New methods for identifying skin cancer are being developed with the help of this research, which can improve patient outcomes and clinical decision-making.

Dental topography of prosimian premolars predicts diet: A comparison in premolar and molar dietary classification accuracies.

This study tests whether (1) premolar topography of extant "prosimians" (strepsirrhines and tarsiers) successfully predicts diet and (2) whether the combination of molar and premolar topography yields higher classification accuracy than using either tooth position in isolation. Dental topographic metrics (ariaDNE, relief index, and orientation patch count rotated) were calculated for 118 individual matched-pairs of mandibular fourth premolars (P4) and second molars (M2). The sample represents 7 families and 22 genera. Tooth variables were analyzed in isolation (P4 only; M2 only), together (P4 and M2), and combined (PC1 scores of bivariate principal component analyses of P4 and M2 for each metric). Discriminant function analyses were conducted with and without a measure of size (two-dimensional surface area). When using topography only, "prosimian" P4 shape predicts diet with a success rate that is slightly higher than that of M2 shape. When absolute size is included, premolars and molars perform comparably well. Including both premolar and molar topography (separately or combined) improves classification accuracy for every analysis beyond considering either in isolation. Classification accuracy is highest when premolar and molar topography and size are included. Our findings indicate that molar teeth incompletely summarize the functional requirements of oral food breakdown for a given diet, and that the mechanism selecting for premolar form is more varied than what is expressed by molar teeth. Finally, our findings suggest that fossil P4s (in isolation or with the M2) can be used for meaningful dietary reconstruction of extinct primates.

Visualization and classification of mushroom species with multi-feature fusion of metaheuristics-based convolutional neural network model

Determining the correct mushroom species with the necessary ecological characteristics is critical to continue mushroom production, which is essential in gastronomy. The mushroom farmers and collectors technique may help identify toxic mushrooms by detecting poisonous mushrooms using images of different mushroom species with distinctive morphological features. However, it can be not easy to distinguish between species. This paper used a dataset of 6714 mushroom images obtained from nine different mushroom species to classify the mushroom species. For a more straightforward comprehension of mushroom images and feature extraction by reanalysis of data sets, data visualization was performed using Grad-CAM, LIME, and Heatmap methods. Residual block-based Convolutional Neural Network (CNN) architectures are trained to automatically classify the concatenated feature map obtained from the Grad-CAM, LIME, and Heatmap methods. After extracting the deep features of the images from each architecture, the Atom Search Optimization (ASO) algorithm has been used to select the most distinctive features. The 6714×9000 size of the concatenated feature map was reduced to 6714×600 using the ASO algorithm. Classification results were evaluated using six different classifiers based on the feature map obtained to determine the mushroom species. The nine classes of mushroom species were classified successfully with 95.45 % accuracy using the proposed model with the ASO algorithm and KNN classifier. The methodology introduces novel visualization techniques for interpreting CNN-based models’ decisions in mushroom species classification tasks. Using metaheuristics-based CNN models with multi-feature fusion techniques allows the model to leverage diverse sources of information, potentially enhancing its ability to discriminate between mushroom species and achieve higher classification accuracy than existing methods. This study can advance the mushroom species classification field by introducing new methodologies, improving classification accuracy, providing insights into model interpretability, and facilitating knowledge transfer to related fields.

Enhanced large-scale building extraction evaluation: developing a two-level framework using proxy data and building matching

ABSTRACT Deep learning-based building extraction methods have widespread applications in diverse fields. However, the evaluation of large-scale extraction results remains challenging, due to traditional evaluation metrics rely on manually created ground-truth samples and the lack of comprehensive reference-building data for developing countries. To address these problems, we proposed a two-level framework for evaluating large-scale footprint extraction. First, we utilised global open-source population and land use data as the proxy data, to assess grid-level completeness for the areas with insufficient reference data. Second, we introduced an improved two-way area-overlapping method to match the extracted footprints with the reference buildings, thereby enabling a comprehensive evaluation of the study region. Tested in Hyogo Prefecture and Numazu City, Japan, the results demonstrated a 2.6-% improvement in grid classification accuracy and an increase of 0.53 in the completeness correlation, compared with the results obtained using a single proxy indicator. Moreover, the optimised matching method achieved an outstanding semantic matching accuracy of 99%, with high efficiency and robustness in multi-scale matching. Therefore, the proposed approach can effectively evaluate large-scale footprint extraction results and interpret their semantic relationship with actual buildings, applicable globally regardless of the availability of reference building datasets.

A2GCN: Graph Convolutional Networks with Adaptive Frequency and Arbitrary Order

Graph Neural Networks (GNNs) gain remarkable success in various graph learning tasks under homophily graph assumption. This assumption is extremely fragile since real-world graphs with heterophily are ubiquitous. Under this circumstance, existing GNNs attempt to design or learn graph spectral filters for observed graphs. The representation ability of them, however, is limited due to: (1) Constant frequency response is incapable of simulating complicated filters that real-world applications require. (2) Fixed polynomial order fails to effectively uncover the node label patterns concealing different order neighborhoods. To this end, we propose a novel Graph Convolutional Networks with Adaptive Frequency and Arbitrary Order (A2GCN) to learn various graph spectral filters suitable for distinct networks. Specifically, a simple but elegant filter with adaptive frequency response is designed to span across multiple layers for capturing different frequency components hiding in varying orders, producing A2GCN filter bases. Afterward, the coefficients of the A2GCN basis for each node are learned to achieve A2GCN filters with arbitrary polynomial order. The resulting A2GCN filters possess flexible frequency response that can automatically adapt to the node label pattern, as such, it empowers A2GCN with stronger expressiveness and naturally alleviates the over-smoothing problem. Theoretical analysis is provided to show the superiority of the proposed A2GCN. Additionally, extensive experiments on both node-level and graph-level tasks validate that the proposed A2GCN accomplishes highly competitive performance and improves classification accuracy. Codes are available at https://github.com/AIG22/A2GCN.

Near-Infrared Spectroscopy Identification Method of Cashmere and Wool Fibers Based on an Optimized Wavelength Selection Algorithm

Cashmere and wool fibers have similar chemical compositions, making them difficult to distinguish based on their absorption peaks and band positions in near-infrared spectroscopy. Existing studies commonly use wavelength selection or feature extraction algorithms to obtain significant spectral features, but traditional algorithms often overlook the correlations between wavelengths, resulting in weak adaptability and local optima issues. To address this problem, this paper proposes a recognition algorithm based on optimal wavelength selection, which can remove redundant information and make the model effective in capturing patterns and key features of the data. The wavelengths are rearranged by computing the information gain ratio for each wavelength. Then, the sorted wavelengths are grouped based on equal density, which ensures that all wavelengths within each group have equal information and avoids over-focusing on individual groups. Meanwhile, the group genetic algorithm is used to find the wavelengths with highly informative and search optimal grouped combinations, in order to explore the entire spectrum wavelength. Finally, combined with a partial least squares discriminant analysis(PLS-DA) model, the recognition accuracy reached 97.3%. The results indicate that, compared to traditional methods such as CARS, SPA, and GA, our method effectively reduces redundant information, selects fewer but more informative wavelengths, and improves classification accuracy and model adaptability.

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.

Research on 3D geological modeling based on boosting integration strategy

Accurate geology modeling is critical in coal mining engineering for increasing mining efficiency and safety. Traditional 3D modeling approaches rely on drill hole data to fill in unknown geographical characteristics using interpolation or machine learning methods. However, the cost of individual borehole projects is high, and borehole distribution is sparse; the filling of sparse boreholes by interpolation smoothes the geologic data to some extent, and some abnormal geologic conditions cannot be shown in the interpolated geologic data; and the classification of subsurface space by machine learning is hampered by sparse training samples and model overfitting or underfitting. As a result, this paper proposes a method to reduce the complexity and uncertainty in the process of 3D geological modeling by integrating the classification results of multiple classifiers based on the machine learning classification model and constructing a 3D geological model based on gas extraction borehole data using the Boosting integration strategy. The results reveal that the Boosting integration model outperforms a single machine learning model in geological modeling, with improved classification accuracy and resilience. A comparative investigation of different classifiers demonstrates that the Boosting integrated model outperforms a single classifier in geological modeling. The geologic profile analysis confirms the dependability and stability of the Boosting integrated model, which can provide an effective solution for 3D geologic modeling of coal mine workings and is critical for increasing mining productivity and lowering accident risks.

Deactivation and collective phasic muscular tuning for pointing direction: Insights from machine learning

Arm movements in our daily lives have to be adjusted for several factors in response to the demands of the environment, for example, speed, direction or distance. Previous research has shown that arm movement kinematics is optimally tuned to take advantage of gravity effects and minimize muscle effort in various pointing directions and gravity contexts. Here we build upon these results and focus on muscular adjustments. We used Machine Learning to analyze the ensemble activities of multiple muscles recorded during pointing in various directions. The advantage of such a technique would be the observation of patterns in collective muscular activity that may not be noticed using univariate statistics. By providing an index of multimuscle activity, the Machine Learning (ML) analysis brought to light several features of tuning for pointing direction. In attempting to trace tuning curves, all comparisons were done with respects to pointing in the horizontal, gravity free plane. We demonstrated that tuning for direction does not take place in a uniform fashion but in a modular manner in which some muscle groups play a primary role. The antigravity muscles were more finely tuned to pointing direction than the gravity muscles. Of note, was their tuning during the first half of downward pointing. As the antigravity muscles were deactivated during this phase, it supported the idea that deactivation is not an on-off function but is tuned to pointing direction. Further support for the tuning of the negative portions of the phasic EMG was provided by the observation of progressively improving classification accuracies with increasing angular distance from the horizontal. We also demonstrated that the durations of these negative phases, without information on their amplitudes, is tuned to pointing directions. Overall, these results show that the motor system tunes muscle commands to exploit gravity effects and reduce muscular effort. It quantitatively demonstrates that phasic EMG negativity is an essential feature of muscle control. The ML analysis was done using Linear Discriminant analysis (LDA) and Support Vector Machines (SVM). The two led to the same conclusions concerning the movements being investigated, hence showing that the former, computationally inexpensive technique is a viable tool for regular investigation of motor control.

Federated Bayesian network approach for cross-regional air pollution classification: a case study of the Beijing-Tianjin-Hebei region.

Although machine learning methods have enabled considerable progress in air quality assessment, challenges persist regarding data privacy, cross-regional data processing, and model generalization. To address these issues, we introduce an advanced federated Bayesian network (FBN) approach. By integrating federated learning, adaptive optimization algorithms, and homomorphic encryption technologies, we substantially enhanced the efficiency and security of cross-regional air quality data processing. The novelty of this research lies in the improvements implemented in federated learning for air quality data analysis, particularly in distributed model training optimization and data consistency. Through the integration of adaptive structural modification strategies and simulated annealing immune optimization algorithms, we markedly enhanced the structural learning accuracy of the Bayesian network, resulting in a 20% improvement in prediction accuracy. Moreover, employing homomorphic encryption ensured data transmission security and confidentiality. In our Beijing-Tianjin-Hebei case study, our method demonstrated a 15% improvement in air quality classification accuracy compared to conventional methods and exhibited superior interpretability in analyzing environmental factor interactions. We quantified complex air pollution patterns across regions and found that a 30% fluctuation in the air quality index correlated with NO2 concentrations. We also observed a moderate positive correlation between specific pollutant indicators in Hebei Province and Tianjin and changes in air quality. Additionally, the FBN exhibited better operational efficiency and data confidentiality than other machine learning models in handling large-scale and multisource environmental data. Our FBN approach presents a novel perspective for environmental monitoring and assessment, vital for understanding complex air pollution patterns and formulating future ecological protection policies.

Peningkatan kinerja arsitektur ResNet50 untuk Menangani Masalah Overfitting dalam Klasifikasi Penyakit Kulit

Skin diseases are a significant global health issue, affecting millions of people worldwide. Deep learning, particularly with the transfer learning approach, has shown great potential in improving the diagnosis of skin diseases. This study aims to evaluate various techniques in the context of skin disease classification using transfer learning, focusing on the utilization of the ResNet50 architecture. The steps include data preprocessing, model design with variations in dense layers, fine-tuning, and dropout, as well as model performance evaluation. The results indicate that adding dense layers and fine-tuning significantly improve classification accuracy. Models without additional dense layers achieved an accuracy of around 90%, while fine-tuned models achieved an accuracy of about 94%, and models with added dense layers and fine-tuning achieved an accuracy of about 92%. Overall, adding dense layers and fine-tuning are effective strategies for enhancing the performance of skin disease classification models.

Using Optuna and Genetic Algorithm together facilitate the classification of plant leaf diseases

The identification and severity assessment of plant leaf diseases is crucial to food security and sustainable agriculture. This study shows an innovative way to improve plant leaf disease detection. The recommended method uses Optuna for parameter optimization and the Genetic Algorithm for feature selection to improve plant leaf disease identification. We do this to improve diagnosis accuracy. This method improves classification accuracy and is called ECPLDD-OGA. Modern hyper parameter optimization framework Optuna is employed. This allows classification model parameters to be fine-tuned. A systematic feature selection method is the Genetic Algorithm. It finds the most useful characteristics in the input dataset. By applying the algorithm on the data. By facilitation, the iterative process helps create a simplified and meaningful subset of features. Contrary to parameter tinkering and feature selection, empirical data suggests that utilizing Optuna and the Genetic Algorithm simultaneously improves disease identification. The updated model recognizes sick plants more accurately and generalizes better. Optimization enabled both gains. The usage of this technology can improve agricultural operations and reduce crop losses by increasing productivity. The present ECPLDD-OGA technique helps integrate hyper parameter tweaking and feature selection into machine learning-based agricultural applications.

Mangrove Species Classification from Unmanned Aerial Vehicle Hyperspectral Images Using Object-Oriented Methods Based on Feature Combination and Optimization.

Accurate and timely acquisition of the spatial distribution of mangrove species is essential for conserving ecological diversity. Hyperspectral imaging sensors are recognized as effective tools for monitoring mangroves. However, the spatial complexity of mangrove forests and the spectral redundancy of hyperspectral images pose challenges to fine classification. Moreover, finely classifying mangrove species using only spectral information is difficult due to spectral similarities among species. To address these issues, this study proposes an object-oriented multi-feature combination method for fine classification. Specifically, hyperspectral images were segmented using multi-scale segmentation techniques to obtain different species of objects. Then, a variety of features were extracted, including spectral, vegetation indices, fractional order differential, texture, and geometric features, and a genetic algorithm was used for feature selection. Additionally, ten feature combination schemes were designed to compare the effects on mangrove species classification. In terms of classification algorithms, the classification capabilities of four machine learning classifiers were evaluated, including K-nearest neighbor (KNN), support vector machines (SVM), random forests (RF), and artificial neural networks (ANN) methods. The results indicate that SVM based on texture features achieved the highest classification accuracy among single-feature variables, with an overall accuracy of 97.04%. Among feature combination variables, ANN based on raw spectra, first-order differential spectra, texture features, vegetation indices, and geometric features achieved the highest classification accuracy, with an overall accuracy of 98.03%. Texture features and fractional order differentiation are identified as important variables, while vegetation index and geometric features can further improve classification accuracy. Object-based classification, compared to pixel-based classification, can avoid the salt-and-pepper phenomenon and significantly enhance the accuracy and efficiency of mangrove species classification. Overall, the multi-feature combination method and object-based classification strategy proposed in this study provide strong technical support for the fine classification of mangrove species and are expected to play an important role in mangrove restoration and management.

Multinomial Logistic Regression with Adaptive Regularization for Cancer Subtype Classification via Multi-omics Data

Background: Integrating multi-omics data for cancer classification brings complementary biological insights while also facing challenges such as data integration, gene grouping, and adaptive weight construction. Objective: This paper aims to address the challenges faced by the cancer subtype classification and gene screening based on multi-omics data. Methods: Multinomial logistic regression with adaptive regularization (MLRAR) was proposed by integrating DNA methylation, gene mutation, and RNA-seq information. A data preprocessing strategy that effectively utilizes multi-omics information was presented, and the local maximum quasiclique merging (lmQCM) algorithm was implemented to group genes. Biological pathway information was utilized to evaluate the significance of gene groups, while the significance of each gene within a group was evaluated by integrating mutation information, information theory, and methylation information. Results: Compared to MRlasso, MRGL, MSGL, MROGL, AMRSOGL, and AGLRMR, the proposed method yielded improvements in subtype classification accuracy of breast cancer by 2.6%, 2.9%, 3.5%, 2.3%, 2.0%, and 1.8%, respectively. In addition, MLRAR also achieved significant improvements in ovarian cancer by 8.2%, 5.0%, 6.8%, 5.2%, 12.7%, and 6.3%, respectively. Conclusion: The proposed method can effectively deal with data integration, gene grouping, and adaptive weight construction.