Multiple Support Vector Machine Research Articles

Integrated sensing and machine learning: Predicting saccharine and bioenergy feedstocks in sugarcane

Predicting saccharine and bioenergy feedstocks in sugarcane enables growers and industries to determine the precise time and location for harvesting a better-quality product in the field. On one hand, Brix, Purity, and total recoverable sugars (TRS) can provide meaningful and reliable indicators of high-quality raw materials for first-generation (1 G) bioethanol. Conversely, Cellulose, Hemicellulose, and Lignin are the primary constituents of straw, directly contributing to second-generation (2G) bioethanol. However, analyzing these materials in the laboratory is a time-consuming and non-scalable task. Therefore, we propose an approach based on a multi-sensor framework, which includes multispectral unmanned aerial vehicle (UAV) imagery, thermal, photosynthetic active radiation (PAR), and chlorophyll fluorescence (ChlF) data, along with machine learning (ML) algorithms namely random forest (RF), multiple linear regression (MLR), decision tree (DT), and support vector machine (SVM), to develop a non-invasive and predictive framework for mapping sugarcane feedstocks. We collected samples of stalks and leaves/straw during the maturity stage while simultaneously collecting remote sensing data. The ML models played a crucial role in predicting 1 G (R2 = 0.88–0.93) and 2 G (R2 = 0.56–0.82) feedstocks. Notably, remote sensing data could serve as important features for the models, mainly through the spectral bands (Blue, Green, and RedEdge), DTemp and ChlF. Hence, the best features can be further implemented within a framework to predict sugarcane feedstocks. Our study marks a significant advancement in the industrial-scale prediction of sugarcane feedstocks, providing stakeholders with invaluable prescriptive harvesting strategies for both primary products and by-products.

Optimal detection and classification of grid connected system using MSVM-FSO technique.

This paper, a hybrid method, is proposed for protecting the hybrid photovoltaic (PV) and wind turbine (WT) system. The proposed protecting method is the hybrid wrapper of both the multiple support vector machine (MSVM) and firebug swarm optimization (FSO), commonly named as MSVM-FSO method. The proposed technique is diagnosing the appropriate fault occurring in the hybrid system. The main purpose of the proposed system is to assure the system with lower complexity for the fault diagnosis and detection (FDD) for improving the power quality (PQ) of hybrid method. Here, the MSVM approach is used to detect the fault conditions of grid-tied system. To evaluate the events of voltages, fault and the currents of hybrid systems are analyzed at the feeder of buses. The FSO categorizes the types of fault, which is occurred in grid-connected system. By then, the proposed method's performance is done in the MATLAB software and it is contrasted with different existing methods. From this, the proposed method provides accuracy as 99.7% and efficiency as 98%, which is high compared to existing methods.

Application of support vector machine system introducing multiple submodels in data mining

As the information age develops, the scale and form of data become more diverse and diverse. Therefore, people need to use effective means to process information. For large-scale data mining problems, a clustering-based kernel matrix inner product filtering method is introduced to decompose the original quadratic programming problem into multiple sub-problems to support parallel training. And a Spark-based multiple submodels parallel support vector machine is proposed. By introducing open-source tools such as OpenCV, image feature extraction can be performed on large-scale video data. Finally, combined with the designed parallel support vector machine algorithm, video facial and expression recognition is carried out. These experiments confirmed that the research method achieved a maximum acceleration ratio of 2090 times when processing Covtype datasets. The research model could achieve an accuracy of over 99 %. Under the maximum data scale experiment, the research model improved prediction accuracy by 21 percentage points with an acceptable additional time cost of about 4 min only. Task parallel processing could more fully utilize cluster performance, increasing by approximately 3.5 m/s2 from 30 to 150 cores. The research model had the highest recognition accuracy for facial expressions, further demonstrating the effectiveness and superiority of this method. The research method has improved the efficiency of big data analysis and mining, and is of great significance in parallel analysis of video data.

Large-Scale Structured Output Classification via Multiple Structured Support Vector Machine by Splitting

Large-Scale Structured Output Classification via Multiple Structured Support Vector Machine by Splitting

Multi-dimensional deep dense residual networks and multiple kernel learning for hyperspectral image classification

To address the issues of inadequate feature expression capacity and poor adaptability of feature fusion in traditional hyperspectral image classification methods, a new approach to classification utilizing a multi-dimensional deep dense residual network and multiple kernel learning is suggested. First, we construct a deep dense residual structure to obtain the spectral, spatial and spectral-spatial features of the image, respectively. Then, the multiple kernel learning is employed to map the three extracted features into the high-dimensional space to achieve the adaptive fusion between features. Finally, multiple kernel support vector machine is adopted to accurately classify the multiple kernel fused features. By randomly selecting 10%, 1% and 1% of samples in each ground object category as training samples, our proposed method demonstrated an enhanced overall classification accuracy of 99.58%, 99.52% and 99.66% according to the experimental results conducted on three typical hyperspectral images. Comparing with some multiple kernel learning based methods, our method can obtain higher classification accuracy. So our method has better recognition ability for hyperspectral image features, and has strong adaptability and robustness.

A stacked multiple kernel support vector machine for blast induced flyrock prediction

As a widely used rock excavation method in civil and mining construction works, the blasting operations and the induced side effects are always investigated by the existing studies. The occurrence of flyrock is regarded as one of the most important issues induced by blasting operations, since the accurate prediction of which is crucial for delineating safety zone. For this purpose, this study developed a flyrock prediction model based on 234 sets of blasting data collected from Sugun Copper Mine site. A stacked multiple kernel support vector machine (stacked MK-SVM) model was proposed for flyrock prediction. The proposed stacked structure can effectively improve the model performance by addressing the importance level of different features. For comparison purpose, 6 other machine learning models were developed, including SVM, MK-SVM, Lagragian Twin SVM (LTSVM), Artificial Neural Network (ANN), Random Forest (RF) and M5 Tree. This study implemented a 5-fold cross validation process for hyperparameters tuning purpose. According to the evaluation results, the proposed stacked MK-SVM model achieved the best overall performance, with RMSE of 1.73 and 1.74, MAE of 0.58 and 1.08, VAF of 98.95 and 99.25 in training and testing phase, respectively.

Quantifying soil organic matter for sustainable agricultural land management with soil color and machine learning technique

AbstractAs interest in sustainable agricultural land management continues to grow, there is a need for advanced techniques that enable easy and rapid quantification of soil characteristics. Soil organic matter (SOM) is a critical factor in determining soil health. Unfortunately, contemporary techniques for SOM content analysis are laborious, time consuming, and resource intensive. In response to this challenge, our study has developed a statistical model for forecasting the SOM content using soil color indices and machine learning algorithms. Color indices, including brightness, hue, and saturation, were derived from the soil images captured by a smartphone. The correlation between color indices and SOM reveals the negative correlations between brightness (−0.790) and hue (−0.420) with the SOM content at significance level (p) <0.01. Conversely, the saturation of soil color, which performed best with the predictive model, exhibited a positive relationship (+0.120, p<0.05). The predictive performance of our model outperformed random forest (RF) algorithm compared to both multiple linear regression (MLR) and support vector machine (SVM). The RF algorithm achieved the highest coefficient of determination (R2) value of 0.984. Furthermore, it demonstrated the lowest error metrics. Notably, the root mean squared error value for the RF algorithm was only 0.025% with the training dataset, whereas the MLR and SVM algorithms yielded relatively higher values at 0.029% and 0.110%, respectively. These findings highlight the presence of a nonlinear relationship in predicting the SOM content, which the RF algorithm effectively captures. This approach offers accurate predictions of the SOM content, supporting sustainable agricultural land management through rapid and easy quantification.

Enhancement of optical surface quality based on real-time compensation of temperature-driven thermal errors in diamond turning

In diamond turning, thermal error compensation is critical for improving machining accuracy. In the ultra-precision diamond turning of optical devices, fluctuations in room temperature cause periodic waviness on the machined surface, which degrades the optical performance. Surface finishing processes, such as polishing, are generally required to remove surface waviness. However, the materials used in the polishing process can pollute the environment. Moreover, the polishing process produces a large amount of waste, including contaminated alcohol and tissue. This study presents a new method for compensating temperature-driven thermal errors during single-point diamond turning (SPDT) using machine learning. Long short-term memory (LSTM), an artificial recurrent neural network architecture, was used to estimate the thermal error from the temperatures observed at several locations around the SPDT machine. The performance of the proposed method was evaluated by comparing its estimation accuracy with those of other machine learning methods (multiple linear regression and support vector machine). The thermal error was compensated for by controlling the tool position according to the estimated thermal error. To evaluate the results of the thermal error compensation, the intensities of the laser beam profiles reflected from two flat aluminum mirrors with diameters of 100 mm were observed at several propagation distances. The waviness formed on the uncompensated surface resulted in a dramatic increase in intensity owing to the constructive interference caused by Bragg scattering, whereas the intensity of the reflection from the compensated surface did not vary as the waviness was removed.

Radar Signal Recognition Based on Bagging SVM

Radar signal recognition under low signal-to-noise ratio (SNR) conditions is a critical issue in modern electronic reconnaissance systems, which face significant challenges in recognition accuracy due to signal diversity. A novel method for radar signal detection based on the bagging support vector machine (SVM) is proposed in this paper.This method firstly utilizes the Choi–Williams distribution (CWD) and the smooth pseudo Wigner-Ville distribution (SPWVD) to obtain different time–frequency images of radar signals, which effectively leverages CWD’s strong time–frequency aggregation and SPWVD’s robust cross-interference resistance. Moreover, histograms of oriented gradient (HOG) features are extracted from time–frequency images to train multiple SVM classifiers by bootstrap sampling. Finally, the performance of each SVM classifier is aggregated using plurality voting to reduce the risk of model overfitting and improve recognition accuracy. We evaluate the effectiveness of the proposed method using 12 different types of radar signals. The experimental results demonstrate that its overall identification rate reaches around 79% at an SNR of −10 dB, and it improves the recognition rate by 5% compared with a single classifier.

Machine learning enabled 2D photonic crystal biosensor for early cancer detection

In this paper, a novel 2D Photonic Crystal (PC)-based cancer biosensor is proposed for the detection of different types of cancer cells HeLa, PC12, MDA, MCF, and Jurkat. The sensor is designed using Silicon-on-insulator (SOI) substrate in a triangular lattice with holes in the slab. The proposed design is optimized to provide a high-quality factor of 15,000, high sensitivity and a low detection limit that are highly effective in cancer detection. Proposed biosensor uses a series of resonant cavities that slice the resonant wavelength to a high peak resonant wavelength with a spectral linewidth of 0.1 nm. The integration of 2D PC biosensors with machine learning techniques for early and accurate cancer detection is optimized for the data set. The performance analysis of Multiple Linear Regression (MLR) and Support Vector Machine (SVM) is studied by repeating training, testing, and optimization of target values (Resonant Wavelength) with dependent and independent features of a 2D PC biosensor system. The SVM modelprovides an R squared value of 0.99 for the biosensor, and the MLR model gave an R squared value of 0.88. TheSVM model provides excellent accuracy in predicting the target values with all the trained input features of a 2D PC biosensing system.

Applications of Machine Learning to Diagnosis of Parkinson's Disease.

Accurate diagnosis of Parkinson's disease (PD) is challenging due to its diverse manifestations. Machine learning (ML) algorithms can improve diagnostic precision, but their generalizability across medical centers in China is underexplored. To assess the accuracy of an ML algorithm for PD diagnosis, trained and tested on data from different medical centers in China. A total of 1656 participants were included, with 1028 from Beijing (training set) and 628 from Fuzhou (external validation set). Models were trained using the least absolute shrinkage and selection operator-logistic regression (LASSO-LR), decision tree (DT), random forest (RF), eXtreme gradient boosting (XGboost), support vector machine (SVM), and k-nearest neighbor (KNN) techniques. Hyperparameters were optimized using five-fold cross-validation and grid search techniques. Model performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, accuracy, sensitivity (recall), specificity, precision, and F1 score. Variable importance was assessed for all models. SVM demonstrated the best differentiation between healthy controls (HCs) and PD patients (AUC: 0.928, 95% CI: 0.908-0.947; accuracy: 0.844, 95% CI: 0.814-0.871; sensitivity: 0.826, 95% CI: 0.786-0.866; specificity: 0.861, 95% CI: 0.820-0.898; precision: 0.849, 95% CI: 0.807-0.891; F1 score: 0.837, 95% CI: 0.803-0.868) in the validation set. Constipation, olfactory decline, and daytime somnolence significantly influenced predictability. We identified multiple pivotal variables and SVM as a precise and clinician-friendly ML algorithm for prediction of PD in Chinese patients.

A novel immune-related prognostic model with surgical status to predict tumor immune cell infiltration and drug sensitivity in head and neck squamous cell carcinoma

Tumor-infiltrating immune cells (TICs) affect tumorigenesis and tumor development in head and neck squamous cell carcinoma (HNSCC). We constructed a novel predictive model for HNSCC based on immune-related genes (IRGs) from The Cancer Genome Atlas and the Immunology Database and Analysis Portal. After identifying the IRGs, a predictive model involving 13 IRGs with high stratification value of overall survival (OS) was constructed by multiple support vector machine recursive feature elimination and least absolute shrinkage and selection operator regression. We explored the relationship between the risk score (RS) and clinical characteristics. The nomogram showed high concordance and good agreement in OS. Four TICs affected the OS and were in agreement with the abundance analysis of the RS levels. Furthermore, the low-risk HNSCC group showed higher expression of PD-1, CTLA4, and TIGIT, while the high-risk group showed higher expression of EGFR. The high-risk HNSCC showed high sensitivity to eight drugs.

Development of Prediction Method for Dimensional Stability of 3D-Printed Objects

Fused deposition modeling (FDM), as one of the additive manufacturing processes, is known for strong layer adhesion suitable for prototypes and end-use items. This study used a multiple regression model and statistical analysis to explore the dimensional accuracy of FDM objects. Factors such as inclination angle, layer thickness, support space, and raster angle were examined. Machine learning models (Gaussian process regression (GPR), support vector machines (SVM), and artificial neural network (ANN)) predicted dimensions using 81 datapoints. The mean squared dimensional error (MSDE) between the measured and designed surface profiles was selected as an output for the dimensional accuracy. Support spacing, layer thickness, and raster angle were determined to be statistically significant, and all factors were confirmed as significant predictors. The coefficients of determination for multiple linear regression, GPR, SVM, and ANN models were 76%, 98%, 93%, and 99%, respectively. The mean absolute errors (MAEs)—errors between the measured and the predicted MSDEs—were 0.020 mm and 0.034 mm, respectively, for GPR and SVM models. The MAEs for ANN models were 0.0055 mm for supporting cases and 2.1468 × 10−5 mm for non-supporting cases.

Prediction of service time for home delivery services using machine learning

With the rise of ready-to-assemble furniture, driven by international giants like IKEA, assembly services were increasingly offered by the same retailers. When planning orders with assembly services, the estimation of the service time leads to additional difficulties compared to standard delivery planning. Assembling large wardrobes or kitchens can take hours or even days while assembling a chair can be done in a few minutes. Combined with the usually vast amounts of offered products, a lot of knowledge is required to plan efficient and exact delivery routes. This paper shows how an artificial neural network (ANN) can be used to accurately predict the service time of a delivery based on factors such as the goods to be delivered or the personnel providing the service. The data used include not only deliveries with assembly of furniture, but also deliveries of goods without assembly and delivery of goods requiring electrical installation. The goal is to create a solution that can predict the time needed based on criteria such the type of furniture, the weight of the goods, and the experiences of the service technicians. The findings show that ANNs can be applied to this scenario and outperform more classical approaches, such as multiple linear regression or support vector machines. Still existing problems are largely due to the provided data, e.g., a large difference between the number of short and longer duration orders, which made it harder to accurately predict orders with longer duration.

A fault diagnosis method for nuclear power plant rotating machinery based on adaptive deep feature extraction and multiple support vector machines

Rotating machinery is the essential component in nuclear power plants (NPPs). Effective fault detection and diagnosis is a main challenge in the operation and maintenance of NPPs rotating machinery. The performance of traditional fault diagnosis methods mainly depends on complex manual feature extraction and sufficient expert prior knowledge. This study proposes a fault diagnosis method based on adaptive feature extraction and multiple support vector machines (ResNet-SVMs) to overcome the limitations of the traditional intelligent fault diagnostics. First, the vibration information from different locations of the rotating machinery is collected and used as input data for the algorithm model. Then, the deep residual neural network adaptively extracts fault features from input data to obtain feature data of different depths. Finally, multiple support vector machines identify the feature data to realize the fault diagnosis. The effectiveness verification is carried out based on the experimental cases of induction motor and rolling bearing fault diagnosis. Compared with other advanced intelligent fault diagnosis methods, ResNet-SVMs model provides better diagnostic performance, which demonstrates its potential value for NPPs rotating machinery fault diagnosis.

Combined DFT and Machine Learning Study of the Dissociation and Migration of H in Pyrrole Derivatives.

Systematic DFT calculations of model coal-pyrrole derivatives substituted by different functional groups are carried out. The N-H bond dissociation energies (N-H BDEs) and H-transfer activation energies (H-TAEs) of pyrrole derivatives are fully evaluated to elucidate the effect of the type of substituents and their position on the molecular reactivity. The results indicate that compounds substituted with electron-donating groups (EDGs) are more prone to pyrolysis while those substituted with electron-withdrawing groups (EWGs) are difficult to pyrolyze. Furthermore, quantitative structure-property relationship (QSPR) models for N-H BDEs and H-TAEs about pyrrole derivatives are built with multiple linear regression (MLR) and support vector machine (SVM). The final results show that the SVM-QSPR model has better fitness, prediction, and robustness, while the MLR-QSPR model can express the physical meaning better. The effects of functional groups on pyrolysis are clarified by the models presented in this paper, which will support the optimization of ultra-low NOx combustion.

A Machine Learning Application for the Energy Flexibility Assessment of a Distribution Network for Consumers

This paper presents a step-by-step approach to assess the energy flexibility potential of residential consumers to manage congestion in the distribution network. A case study is presented where a selected transformer station exhibits signs of overloading. An analysis has been performed to evaluate the magnitude of the overloading and the timing of the overload occurrence based on their historical load data. Based on the historical load data, the four most prominent consumers have been chosen for the flexibility assessment. Temperature load dependency has been evaluated for the selected consumers. The paper’s novel approach focuses on selecting individual consumers with the highest energy flexibility potential, and analysing their load patterns to address transformer overloading. To achieve this, machine learning algorithms, specifically, multiple linear regression and support vector machines, were used for load profile forecasting during the overload occurrences. Based on the forecast and measured load patterns, flexibility scenarios were created for each consumer. The generated models were evaluated and compared with the forecasting based on the average load of the past days. In the results, three potential consumers were identified who could resolve the transformer overloading problem. The machine learning models outperformed the average-based forecasting method, providing more realistic estimates of flexibility potential. The proposed approach can be applied to other overloaded transformer stations, but with a limited number of consumers.

Optimizing and extending ion dielectric polarizability database for microwave frequencies using machine learning methods

Permittivity at microwave frequencies determines the practical applications of microwave dielectric ceramics. The accuracy and universality of the permittivity prediction by Clausius–Mossotti equation depends on the dielectric polarizability (αD) database. The most influential αD database put forward by Shannon is facing three challenges in the 5 G era: (1) Few data, (2) Simplistic relation and (3) Low frequency (kHz–MHz) oriented. Here, we optimized and extended the Shannon’s database for microwave frequencies by the four-stage multiple linear regression and support vector machine model. In comparison with the conventional database, the optimized and extended databases achieved higher accuracy and expanded the amount of data from 60 to more than 900. Besides, we analyzed the relationships between αD and ion characteristics, including ionic radius (IR), atomic number (N), valence state (V) and coordination number (CN). We found that the positive cubic law of “αD ~ IR3” discussed in Shannon’s work was valid for the IR changed by the N, but invalid for the change caused by the CN.

LINC01137/miR-186-5p/WWOX: a novel axis identified from WWOX-related RNA interactome in bladder cancer.

Introduction: The discovery of non-coding RNA (ncRNA) dates back to the pre-genomics era, but the progress in this field is still dynamic and leverages current post-genomics solutions. WWOX is a global gene expression modulator that is scarcely investigated for its role in regulating cancer-related ncRNAs. In bladder cancer (BLCA), the link between WWOX and ncRNA remains unexplored. The description of AP-2α and AP-2γ transcription factors, known as WWOX-interacting proteins, is more commonplace regarding ncRNA but still merits investigation. Therefore, this in vitro and in silico study aimed to construct an ncRNA-containing network with WWOX/AP-2 and to investigate the most relevant observation in the context of BLCA cell lines and patients. Methods: RT-112, HT-1376, and CAL-29 cell lines were subjected to two stable lentiviral transductions. High-throughput sequencing of cellular variants (deposited in the Gene Expression Omnibus database under the GSE193659 record) enabled the investigation of WWOX/AP-2-dependent differences using various bioinformatics tools (e.g., limma-voom, FactoMineR, multiple Support Vector Machine Recursive Feature Elimination (mSVM-RFE), miRDB, Arena-Idb, ncFANs, RNAhybrid, TargetScan, Protein Annotation Through Evolutionary Relationships (PANTHER), Gene Transcription Regulation Database (GTRD), or Evaluate Cutpoints) and repositories such as The Cancer Genome Atlas (TCGA) and Cancer Cell Line Encyclopedia. The most relevant observations from cap analysis gene expression sequencing (CAGE-seq) were confirmed using real-time PCR, whereas TCGA data were validated using the GSE31684 cohort. Results: The first stage of the whole study justified focusing solely on WWOX rather than on WWOX combined with AP-2α/γ. The most relevant observation of the developed ncRNA-containing network was LINC01137, i.e., long non-coding RNAs (lncRNAs) that unraveled the core network containing UPF1, ZC3H12A, LINC01137, WWOX, and miR-186-5p, the last three being a novel lncRNA/miRNA/mRNA axis. Patients' data confirmed the LINC01137/miR-186-5p/WWOX relationship and provided a set of dependent genes (i.e., KRT18, HES1, VCP, FTH1, IFITM3, RAB34, and CLU). Together with the core network, the gene set was subjected to survival analysis for both TCGA-BLCA and GSE31684 patients, which indicated that the increased expression of WWOX or LINC01137 is favorable, similar to their combination with each other (WWOX↑ and LINC01137↑) or with MIR186 (WWOX↑/LINC01137↑ but MIR186↓). Conclusion: WWOX is implicated in the positive feedback loop with LINC01137 that sponges WWOX-targeting miR-186-5p. This novel WWOX-containing lncRNA/miRNA/mRNA axis should be further investigated to depict its relationships in a broader context, which could contribute to BLCA research and treatment.

Identification of mitochondrial related signature associated with immune microenvironment in Alzheimer’s disease

BackgroundAlzheimer's disease (AD) is the most common neurodegenerative disease. Mitochondrial dysfunction and immune responses are important factors in the pathogenesis of AD, but their crosstalk in AD has not been studied. In this study, the independent role and interaction of mitochondria-related genes and immune cell infiltration in AD were investigated using bioinformatics methods.MethodsThe datasets of AD were obtained from NCBI Gene Expression Omnibus (GEO), and the data of mitochondrial genes was from MitoCarta3.0 database. Subsequently, differential expression genes (DEGs) screening and GSEA functional enrichment analysis were performed. The intersection of DEGs and mitochondrial related genes was used to obtain MitoDEGs. The MitoDEGs most relevant to AD were determined by Least absolute shrinkage and selection operator and multiple support vector machine recursive feature elimination, as well as protein–protein interactions (PPI) network and random forest. The infiltration of 28 kinds of immune cells in AD was analyzed by ssGSEA, and the relationship between hub MitoDEGs and the proportion of immune infiltration was studied. The expression levels of hub MitoDEGs were verified in cell models and AD mice, and the role of OPA1 in mitochondrial damage and neuronal apoptosis was investigated.ResultsThe functions and pathways of DEGs were significantly enriched in AD, including immune response activation, IL1R pathway, mitochondrial metabolism, oxidative damage response and electron transport chain-oxphos system in mitochondria. Hub MitoDEGs closely related to AD were obtained based on PPI network, random forest and two machine learning algorithms. Five hub MitoDEGs associated with neurological disorders were identified by biological function examination. The hub MitoDEGs were found to be correlated with memory B cell, effector memory CD8 T cell, activated dendritic cell, natural killer T cell, type 17 T helper cell, Neutrophil, MDSC, plasmacytoid dendritic cell. These genes can also be used to predict the risk of AD and have good diagnostic efficacy. In addition, the mRNA expression levels of BDH1, TRAP1, OPA1, DLD in cell models and AD mice were consistent with the results of bioinformatics analysis, and expression levels of SPG7 showed a downward trend. Meanwhile, OPA1 overexpression alleviated mitochondrial damage and neuronal apoptosis induced by Aβ1-42.ConclusionsFive potential hub MitoDEGs most associated with AD were identified. Their interaction with immune microenvironment may play a crucial role in the occurrence and prognosis of AD, which provides a new insight for studying the potential pathogenesis of AD and exploring new targets.