Advanced Network Model Research Articles

Optimizing deep neural network architectures for renewable energy forecasting

An accurate renewable energy output forecast is essential for energy efficiency and power system stability. Long Short-Term Memory(LSTM), Bidirectional LSTM(BiLSTM), Gated Recurrent Unit(GRU), and Convolutional Neural Network-LSTM(CNN-LSTM) Deep Neural Network (DNN) topologies are tested for solar and wind power production forecasting in this study. ARIMA was compared to the models. This study offers a unique architecture for Deep Neural Networks (DNNs) that are specifically tailored for renewable energy forecasting, optimizing accuracy by advanced hyperparameter tuning and the incorporation of essential meteorological and temporal variables. The optimized LSTM model outperformed others, with MAE (0.08765), MSE (0.00876), RMSE (0.09363), MAPE (3.8765), and R2 (0.99234) values. The GRU, CNN-LSTM, and BiLSTM models predicted well. Meteorological and time-based factors enhanced model accuracy. The addition of sun and wind data improved its prediction. The results show that advanced deep neural network (DNN) models can predict renewable energy, highlighting the importance of carefully selecting characteristics and fine-tuning the model. This work improves renewable energy estimates to promote a more reliable and environmentally sustainable electricity system.

Advanced CNN models in gastric cancer diagnosis: enhancing endoscopic image analysis with deep transfer learning.

The rapid advancement of science and technology has significantly expanded the capabilities of artificial intelligence, enhancing diagnostic accuracy for gastric cancer. This research aims to utilize endoscopic images to identify various gastric disorders using an advanced Convolutional Neural Network (CNN) model. The Kvasir dataset, comprising images of normal Z-line, normal pylorus, ulcerative colitis, stool, and polyps, was used. Images were pre-processed and graphically analyzed to understand pixel intensity patterns, followed by feature extraction using adaptive thresholding and contour analysis for morphological values. Five deep transfer learning models-NASNetMobile, EfficientNetB5, EfficientNetB6, InceptionV3, DenseNet169-and a hybrid model combining EfficientNetB6 and DenseNet169 were evaluated using various performance metrics. For the complete images of gastric cancer, EfficientNetB6 computed the top performance with 99.88% accuracy on a loss of 0.049. Additionally, InceptionV3 achieved the highest testing accuracy of 97.94% for detecting normal pylorus, while EfficientNetB6 excelled in detecting ulcerative colitis and normal Z-line with accuracies of 98.8% and 97.85%, respectively. EfficientNetB5 performed best for polyps and stool with accuracies of 98.40% and 96.86%, respectively.The study demonstrates that deep transfer learning techniques can effectively predict and classify different types of gastric cancer at early stages, aiding experts in diagnosis and detection.

Predicting Economic Trends and Stock Market Prices with Deep Learning and Advanced Machine Learning Techniques

The volatile and non-linear nature of stock market data, particularly in the post-pandemic era, poses significant challenges for accurate financial forecasting. To address these challenges, this research develops advanced deep learning and machine learning algorithms to predict financial trends, quantify risks, and forecast stock prices, focusing on the technology sector. Our study seeks to answer the following question: “Which deep learning and supervised machine learning algorithms are the most accurate and efficient in predicting economic trends and stock market prices, and under what conditions do they perform best?” We focus on two advanced recurrent neural network (RNN) models, long short-term memory (LSTM) and Gated Recurrent Unit (GRU), to evaluate their efficiency in predicting technology industry stock prices. Additionally, we integrate statistical methods such as autoregressive integrated moving average (ARIMA) and Facebook Prophet and machine learning algorithms like Extreme Gradient Boosting (XGBoost) to enhance the robustness of our predictions. Unlike classical statistical algorithms, LSTM and GRU models can identify and retain important data sequences, enabling more accurate predictions. Our experimental results show that the GRU model outperforms the LSTM model in terms of prediction accuracy and training time across multiple metrics such as RMSE and MAE. This study offers crucial insights into the predictive capabilities of deep learning models and advanced machine learning techniques for financial forecasting, highlighting the potential of GRU and XGBoost for more accurate and efficient stock price prediction in the technology sector.

Remote sensing of depth-induced variations in soil organic carbon stocks distribution within different vegetated landscapes

The preservation and augmentation of soil organic carbon (SOC) stocks is critical to designing climate change mitigation strategies and alleviating global warming. However, due to the susceptibility of SOC stocks to environmental and topo-climatic variability and changes, it is essential to obtain a comprehensive understanding of the state of current SOC stocks both spatially and vertically. Consequently, to effectively assess SOC storage and sequestration capacity, precise evaluations at multiple soil depths are required. Hence, this study implemented an advanced Deep Neural Network (DNN) model incorporating Sentinel-1 Synthetic Aperture Radar (SAR) data, topo-climatic features, and soil physical properties to predict SOC stocks at multiple depths (0–30 cm, 30–60 cm, 60–100 cm, and 100–200 cm) across diverse land-use categories in the KwaZulu-Natal province, South Africa. There was a general decline in the accuracy of the DNN model’s prediction with increasing soil depth, with the root mean square error (RMSE) ranging from 8.34 t/h to 11.97 t/h for the four depths. These findings imply that the link between environmental covariates and SOC stocks weakens with soil depth. Additionally, distinct factors driving SOC stocks were discovered in both topsoil and deep-soil, with vegetation having the strongest effect in topsoil, and topo-climate factors and soil physical properties becoming more important as depth increases. This underscores the importance of incorporating depth-related soil properties in SOC modelling. Grasslands had the largest SOC stocks, while commercial forests have the highest SOC sequestration rates per unit area. This study offers valuable insights to policymakers and provides a basis for devising regional management strategies that can be used to effectively mitigate climate change.

Elucidating transport dynamics and regional division of PM2.5 and O3 in China using an advanced network model

Air pollution exhibits significant spatial spillover effects, complicating and challenging regional governance models. This study innovatively applied and optimized a statistics-based complex network method in atmospheric environmental field. The methodology was enhanced through improvements in edge weighting and threshold calculations, leading to the development of an advanced pollutant transport network model. This model integrates pollution, meteorological, and geographical data, thereby comprehensively revealing the dynamic characteristics of PM2.5 and O3 transport among various cities in China. Research findings indicated that, throughout the year, the O3 transport network surpassed the PM2.5 network in edge count, average degree, and average weighted degree, showcasing a higher network density, broader city connections, and greater transmission strength. Particularly during the warm period, these characteristics of the O3 network were more pronounced, showcasing significant transport potential. Furthermore, the model successfully identified key influential cities in different periods; it also provided detailed descriptions of the interprovincial spillover flux and pathways of PM2.5 and O3 across various time scales. It pinpointed major pollution spillover and receiving provinces, with primary spillover pathways concentrated in crucial areas such as the Beijing-Tianjin-Hebei (BTH) region and its surrounding areas, the Yangtze River Delta, and the Fen-Wei Plain. Building on this, the model divided the O3, PM2.5, and synergistic pollution transmission regions in China into 6, 7, and 8 zones, respectively, based on network weights and the Girvan Newman (GN) algorithm. Such division offers novel perspectives and strategies for regional joint prevention and control. The validity of the model was further corroborated by source analysis results from the WRF-CAMx model in the BTH area. Overall, this research provides valuable insights for local and regional atmospheric pollution control strategies. Additionally, it offers a robust analytical tool for research in the field of atmospheric pollution.

Enhancing Plant Disease Detection using Advanced Deep Learning Models

Objective: The aim of this paper is to analyze the efficacy of employing multiple advanced convolutional neural networks (CNNs) for the purpose of enhancing the accuracy in detecting and classifying various plant diseases. Methods: The research involves the analysis of 7623 training images as well as 1906 validation images of different plant diseases and employed advanced deep learning models like DenseNet169, Xception, InceptionV3, MobileNetV2, and ResNet50V2 to classify them. At first the RGB images are converted to Grayscale and later to enhance their quality, few techniques have been used such as Otsu thresholding, noise removal, distance transform, and watershed techniques. Subsequently, contour features are extracted by calculating morphological values to obtain the necessary region that correspond to diseased areas in plant images. Findings: On evaluating the performance of the applied models on the basis of various metrics, MobileNetV2 and ResNetV2 achieved the highest validation accuracy scores of 99.42% each, with their respective loss values of 0.19 and 0.49. In terms of recall, precision, and F1 score, all models, except MobileNetV2 and InceptionV3, attained optimal scores of 0.99 each. Novelty: The novelty of this paper resides in the incorporation of multiple image segmentation techniques with fine tuning the parameters of advanced Convolutional Neural Network (CNN) models on the basis of various factors such as the number of images, size, channel, classes etc to generate the optimal results. Keywords: Agriculture, Plant diseases, Artificial Intelligence, Advanced CNN models, Watershed Technique

Causality-embedded reconstruction network for high-resolution fault identification in chemical process

Fault identification is essential for analyzing the root causes and propagation of faults. Traditional identification based on contribution plots often suffer from the smearing effect, a phenomenon where the residuals of fault variables smearing over other non-fault process variables due to the complex interconnections within the processes, potentially leading to ambiguous or inaccurate diagnosis. To address this, we propose the Causality-Embedded Reconstruction Network (CERN) based high-resolution fault identification for chemical process. CERN is an advanced graph network model that embeds causality, featuring a dual-decoding scheme comprising a causal decoder and an attribute decoder. This design ensures that feature reconstruction is guided by variables with established causal relationships, effectively isolating the feature representations of normal variables from the influence of fault variables that lack a causal connection. By leveraging this causality-embedded reconstruction, the smearing effect can be alleviated. Experiments conducted on a Continuous Stirred-Tank Reactor system and a real-world Continuous Catalytic Reforming process to demonstrate that the proposed CERN-based fault identification method not only improves the accuracy in identifying fault variables but also offers explanatory insights and traceability for fault diagnosis, showing prospects for industrial process safety.

Joint-Module Health Status Recognition for an Unmanned Platform: A Time–Frequency Representation and Extraction Network-Based Approach

Due to the complex structure of the joint module and harsh working conditions of unmanned platforms, the fault information is often overwhelmed by noise. Moreover, traditional mechanical health state recognition methods usually require a large amount of labeled data in advance, which is difficult to obtain for specific fault data in engineering applications. This limited amount of fault data restricts the diagnostic performance. Additionally, the characteristics of convolutional neural networks (CNNs) limit their ability to capture the relative positional information of fault features. In order to obtain more comprehensive fault information, this paper proposes an intelligent health state recognition method for unmanned platform joint modules based on feature modal decomposition (FMD) and the enhanced capsule network. Firstly, the collected vibration signals are decomposed into a series of feature modal components using FMD. Then, time–frequency maps containing significant fault features are generated based on the continuous wavelet transform (CWT). Finally, a multi-scale feature enhancement (MLFE) module and an efficient channel attention (ECA) module are proposed to enhance the feature extraction capability of the capsule network, extracting more comprehensive global and local feature information from the time–frequency maps to achieve the intelligent state recognition of joint modules. This approach enhances fault features while reducing the impact of redundant features, significantly improving the feature extraction capability without increasing the model’s computational complexity. The effectiveness and superiority of the proposed method are validated through experiments on an unmanned platform joint-module testbed. An ablation experiment demonstrates the effectiveness of the MLFE and ECA modules, and a comparison with other advanced network models proves the superiority of the proposed method for health status recognition.

Optimization of pneumonia CT classification model using RepVGG and spatial attention features.

Pneumonia is a common and widespread infectious disease that seriously affects the life and health of patients. Especially in recent years, the outbreak of COVID-19 has caused a sharp rise in the number of confirmed cases of epidemic spread. Therefore, early detection and treatment of pneumonia are very important. However, the uneven gray distribution and structural intricacy of pneumonia images substantially impair the classification accuracy of pneumonia. In this classification task of COVID-19 and other pneumonia, because there are some commonalities between this pneumonia, even a small gap will lead to the risk of prediction deviation, it is difficult to achieve high classification accuracy by directly using the current network model to optimize the classification model. Consequently, an optimization method for the CT classification model of COVID-19 based on RepVGG was proposed. In detail, it is made up of two essential modules, feature extraction backbone and spatial attention block, which allows it to extract spatial attention features while retaining the benefits of RepVGG. The model's inference time is significantly reduced, and it shows better learning ability than RepVGG on both the training and validation sets. Compared with the existing advanced network models VGG-16, ResNet-50, GoogleNet, ViT, AlexNet, MobileViT, ConvNeXt, ShuffleNet, and RepVGG_b0, our model has demonstrated the best performance in a lot of indicators. In testing, it achieved an accuracy of 0.951, an F1 score of 0.952, and a Youden index of 0.902. Overall, multiple experiments on the large dataset of SARS-CoV-2 CT-scan dataset reveal that this method outperforms most basic models in terms of classification and screening of COVID-19 CT, and has a significant reference value. Simultaneously, in the inspection experiment, this method outperformed other networks with residual structures.

Edge Artificial Intelligence-Based Facial Pain Recognition During Myocardial Infarction

Medical history highlights that Myocardial Infarction is one of the leading factors of death in human beings. Angina pectoris is a prominent vital sign of Myocardial Infraction. Medical reports suggests that experiencing a chest pain during heart attacks causes changes in facial muscles resulting in variations in patterns of facial expression. The present work intends to develop an automatic facial expression detection to identify the severity of chest pain as a vital signs of MI using algorithmic approach that is implemented with a state of art Convolution Neural Networks CNN. The advanced object detection light weight Convolutional Neural Network models: Single Shot Detector Mobile Net V2 and Single Shot Detector Inception V2 are utilized for designing the vital signs MI model from 500 Red Blue Green Color images private dataset. The authors develop a cardiac emergency health monitoring care using an Edge Artificial Intelligence, “Edge AI” using NVIDIA’s Jetson Nano embedded GPU platform. The proposed model is mainly focused on the low cost and less power consumption factors for onboard real time detection of vital signs of Myocardial infarction. The evaluated metrics achieves a mean Average Precision of 85.18%, Average Recall of 88.32% and 6.85 frames per second for the generated detections.

Online monitoring of crack dynamic development using attention-based deep networks

Crack inspection is an essential means to guarantee the healthy service state of infrastructure. However, conventional methods suffer from bottlenecks such as wide blind inspection areas and low efficiency, which make it difficult to reveal the real-time development of cracks. This paper proposes an online crack analysis framework based on deep learning, aiming to effectively broaden the inspectable area and provide real-time feedback on crack development information. The proposed framework includes: (1) Lightweight attention-based crack segmentation U-shape network (CrackSeU). CrackSeU, in comparison to conventional segmentation networks, demonstrates improved fusion between multi-level and multi-scale features. According to the experimental results, CrackSeU achieves enhanced crack segmentation with reduced computation and parameters compared to several advanced network models. (2) Simple and efficient quantitative characterization algorithm. In light of the crack segmentation results, the algorithm can further quantify the actual size of cracks in the physical world, which is convenient for engineers to grasp the structural security status. (3) An online crack monitoring system incorporating the above algorithms. It enables visualization and quantitative monitoring of crack development and establishes a solid foundation for structural safety evaluation. The engineering feasibility and broad application prospect of the proposed framework are further verified by an indoor full-scale concrete beam loading test.

CNN-Transformer for Microseismic Signal Classification

The microseismic signals of coal and rock fractures collected by underground sensors contain masses of blasting vibration signals generated by coal mine blasting, and the waveforms of the two signals are highly similar. In order to identify the true microseismic signals with a microseismic monitoring system quickly and accurately, this paper proposes a lightweight network model that combines a convolutional neural network (CNN) and transformer, named CCViT. Of these, the CNN is used to extract shallow features locally, and the transformer is used to extract deep features globally. Moreover, a modified channel attention module provides important channel information for the model and suppresses useless information. The experimental results on the dataset used in this paper show that the proposed CCViT model has significant advantages for floating point operations (FLOPs), parameter quantity, and accuracy compared to many advanced network models.

Building Change Detection with Deep Learning by Fusing Spectral and Texture Features of Multisource Remote Sensing Images: A GF-1 and Sentinel 2B Data Case

Building change detection is an important task in the remote sensing field, and the powerful feature extraction ability of the deep neural network model shows strong advantages in this task. However, the datasets used for this study are mostly three-band high-resolution remote sensing images from a single data source, and few spectral features limit the development of building change detection from multisource remote sensing images. To investigate the influence of spectral and texture features on the effect of building change detection based on deep learning, a multisource building change detection dataset (MS-HS BCD dataset) is produced in this paper using GF-1 high-resolution remote sensing images and Sentinel-2B multispectral remote sensing images. According to the different resolutions of each Sentinel-2B band, eight different multisource spectral data combinations are designed, and six advanced network models are selected for the experiments. After adding multisource spectral and texture feature data, the results show that the detection effects of the six networks improve to different degrees. Taking the MSF-Net network as an example, the F1-score and IOU improved by 0.67% and 1.09%, respectively, compared with high-resolution images, and by 7.57% and 6.21% compared with multispectral images.

A Quantitative Structure-Activity Relationship for Human Plasma Protein Binding: Prediction, Validation and Applicability Domain.

The purpose of this study was to develop a robust and externally predictive in silico QSAR-neural network model for predicting plasma protein binding of drugs. This model aims to enhance drug discovery processes by reducing the need for chemical synthesis and extensive laboratory testing. A dataset of 277 drugs was used to develop the QSAR-neural network model. The model was constructed using a Filter method to select 55 molecular descriptors. The validation set's external accuracy was assessed through the predictive squared correlation coefficient Q2 and the root mean squared error (RMSE). The developed QSAR-neural network model demonstrated robustness and good applicability domain. The external accuracy of the validation set was high, with a predictive squared correlation coefficient Q2 of 0.966 and a root mean squared error (RMSE) of 0.063. Comparatively, this model outperformed previously published models in the literature. The study successfully developed an advanced QSAR-neural network model capable of predicting plasma protein binding in human plasma for a diverse set of 277 drugs. This model's accuracy and robustness make it a valuable tool in drug discovery, potentially reducing the need for resource-intensive chemical synthesis and laboratory testing.

Segmentation Detection Method for Complex Road Cracks Collected by UAV Based on HC-Unet++

Road cracks are one of the external manifestations of safety hazards in transportation. At present, the detection and segmentation of road cracks is still an intensively researched issue. With the development of image segmentation technology of the convolutional neural network, the identification of road cracks has also ushered in new opportunities. However, the traditional road crack segmentation method has these three problems: 1. It is susceptible to the influence of complex background noise information. 2. Road cracks usually appear in irregular shapes, which increases the difficulty of model segmentation. 3. The cracks appear discontinuous in the segmentation results. Aiming at these problems, a network segmentation model of HC-Unet++ road crack detection is proposed in this paper. In this network model, a deep parallel feature fusion module is first proposed, one which can effectively detect various irregular shape cracks. Secondly, the SEnet attention mechanism is used to eliminate complex backgrounds to correctly extract crack information. Finally, the Blurpool pooling operation is used to replace the original maximum pooling in order to solve the crack discontinuity of the segmentation results. Through the comparison with some advanced network models, it is found that the HC-Unet++ network model is more precise for the segmentation of road cracks. The experimental results show that the method proposed in this paper has achieved 76.32% mIOU, 82.39% mPA, 85.51% mPrecision, 70.26% dice and Hd95 of 5.05 on the self-made 1040 road crack dataset. Compared with the advanced network model, the HC-Unet++ network model has stronger generalization ability and higher segmentation accuracy, which is more suitable for the segmentation detection of road cracks. Therefore, the HC-Unet++ network model proposed in this paper plays an important role in road maintenance and traffic safety.

Robust Hierarchical Scheduling Approach to Coordinate Wind Power Penetrated Transmission System and LNG Railway Transportation

Rail transport of liquefied natural gas (LNG), as an essential means of transmitting energy across regions, has been widely implemented and promoted. The significant growth of gas-fired power and power-to-gas units has intensified the interaction and interdependency between wind power penetrated transmission system and LNG transported railway network. Hence, a robust and hierarchical scheduling approach to coordinate the transmission system and LNG railway transportation is innovatively proposed. First, an advanced time-space network (TSN) model is established with additional security constraints to exactly simulate the railway traffic. Then, a two-stage robust scheduling model is formulated with an uncertainty set incorporating random components failures of the transmission system and the railway network as well as variability of wind power and loads. Subsequently, the two-stage robust scheduling problem is decomposed into two interactive levels according to the analytical target cascading (ATC) technique, thus ensuring the information privacy and decision independency of the power and railway systems. Finally, an ATC-based hierarchical solution framework embedded with the column-and-constraint generation (C&CG) algorithm is presented to solve the proposed model. Case studies demonstrate the effectiveness and benefit of collaboratively managing the power and railway systems.

Improving Modulation Recognition Using Time Series Data Augmentation via a Spatiotemporal Multi-Channel Framework

Automatic modulation recognition technology with deep learning has a broad prospective owing to big data and computing power. However, the accuracy of modulation recognition largely depends on the massive volume of data and the applicability of the model. Here, to eliminate the difficulties of manual feature extraction, a low accuracy, and a small sample dataset, we propose an effective recognition method that combines time series data augmentation with a spatiotemporal multi-channel learning framework. Compared with other advanced network models, the results showed that the method gave a positive index in the order of 93.5% for ten modulation signal types, which was increased by at least 15%. Especially for QAM16 and QAM64 signals, the average recognition accuracy was improved by nearly 50% at SNRs as low as −2 dB, showing a significant recognition performance. The proposed method provides an attractive method for signal modulation recognition in wireless or wired communication fields.

Simple Growth-Metabolism Relations Are Revealed by Conserved Patterns of Heat Flow from Cultured Microorganisms.

Quantitative analyses of cell replication address the connection between metabolism and growth. Various growth models approximate time-dependent cell numbers in culture media, but physiological implications of the parametrizations are vague. In contrast, isothermal microcalorimetry (IMC) measures with unprecedented sensitivity the heat (enthalpy) release via chemical turnover in metabolizing cells. Hence, the metabolic activity can be studied independently of modeling the time-dependence of cell numbers. Unexpectedly, IMC traces of various origins exhibit conserved patterns when expressed in the enthalpy domain rather than the time domain, as exemplified by cultures of Lactococcus lactis (prokaryote), Trypanosoma congolese (protozoan) and non-growing Brassica napus (plant) cells. The data comply extraordinarily well with a dynamic Langmuir adsorption reaction model of nutrient uptake and catalytic turnover generalized here to the non-constancy of catalytic capacity. Formal relations to Michaelis–Menten kinetics and common analytical growth models are briefly discussed. The proposed formalism reproduces the “life span” of cultured microorganisms from exponential growth to metabolic decline by a succession of distinct metabolic phases following remarkably simple nutrient–metabolism relations. The analysis enables the development of advanced enzyme network models of unbalanced growth and has fundamental consequences for the derivation of toxicity measures and the transferability of metabolic activity data between laboratories.

Evaluation of the ultimate eccentric load of rectangular CFSTs using advanced neural network modeling

In this paper an Artificial Neural Network (ANN) model is developed for the prediction of the ultimate compressive load of rectangular Concrete Filled Steel Tube (CFST) columns, taking into account load eccentricity. To this end, an experimental database of CFST specimens from the literature has been compiled, totaling 1224 individual tests, both under concentric and under eccentric loading. Except for eccentricity, other parameters taken into consideration include the cross section width, height and thickness, the steel yield limit, the concrete strength and the column length. Both short and long specimens were evaluated. The architecture of the proposed ANN model was optimally selected, according to predefined performance metrics. The developed model was then compared against available design codes. It was found that its accuracy was significantly improved while maintaining a stable numerical behavior. The explicit equation that describes mathematically the ANN is offered in the paper, for easier implementation and evaluation purposes.

Aberrant Development of Cross-Frequency Multiplex Functional Connectome in First-Episode, Drug-Naive Major Depressive Disorder and Schizophrenia.

Introduction: Both major depressive disorder (MDD) and schizophrenia (SCH) are characterized by neurodevelopmental abnormalities; however, transdiagnostic and diagnosis-specific patterns of such abnormalities have rarely been examined, particularly in large-scale functional brain networks via advanced multilayer network models. Methods: Here, we collected resting-state functional magnetic resonance imaging data from 45 MDD patients, 64 SCH patients, and 48 healthy controls (HCs; 13-45 years old), and we constructed functional networks in different frequency intervals. The frequency-dependent networks were then fused by multiplex network models, followed by graph-based topological analyses. Results: We found that functional networks of the patients showed common neurodevelopmental abnormalities in the right ventromedial parietooccipital sulcus (opposite correlations with age to HCs), whereas functional networks of the MDD patients exhibited specific alterations in the left superior parietal lobule and right precentral gyrus with respect to cross-frequency interactions. These findings were quite different from those from brain networks within each frequency interval, which revealed SCH-specific neurodevelopmental abnormalities in the right superior temporal gyrus (opposite correlations with age to the other two groups) in 0.027-0.073 Hz, and SCH-specific alterations in the left superior temporal gyrus and bilateral insula in 0.073-0.198 Hz. Finally, multivariate analysis of age prediction revealed that the subcortical network lost prediction ability in both patient groups, whereas the visual network exhibited additional prediction ability in the MDD patients. Discussion and Conclusion: Altogether, these findings demonstrate transdiagnostic and diagnosis-specific neurodevelopmental abnormalities and alterations in large-scale functional brain networks between MDD and SCH, which have important implications for understanding shared and unique neural mechanisms underlying the diseases.