Deep Learning Neural Network Model Research Articles

Enhancing streamflow drought prediction: integrating wavelet decomposition with deep learning and quantile regression neural network models

Drought is a significant natural hazard that severely challenges water resource management and agricultural sustainability. This study aims to propose a novel approach for predicting streamflow drought indices (SDI-3, SDI-6, and SDI-12) in humid continental (Stockholm) and semi-arid (ELdiem) climates at different time-steps. The approach utilizes a Quantile Regression Neural Network (QRNN) coupled with wavelet decomposition (WD) techniques. Six mother wavelets (haar, sym8, coif5, bior6.8, demy, and db10) were used to decompose the SDI time series into different frequency bands, helping to identify patterns and trends in drought signals. The QRNN was compared with a tree-based machine learning (ML) model and two deep learning models: Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). Results from stand-alone models showed that the LSTM model outperformed others in predicting SDI-3, while the QRNN model performed best in predicting SDI-6 and SDI-12 in both study regions. In the Stockholm station, the hybrid models achieved acceptable accuracy with bior6.8-LSTM2 (Nash–Sutcliffe efficiency (NSE) = 0.927), bior6.8-QRNN2 (NSE = 0.962), and demy-QRNN2 (NSE = 0.984) performing best for SDI-3, SDI-6, and SDI-12 predictions during the test phase, respectively. For the ELdiem station, the db10-QRNN3 (NSE = 0.926), demy-QRNN3 (NSE = 0.934), and demy-QRNN2 (NSE = 0.981) models demonstrated superior performance during the test phase in predicting SDI-3, SDI-6, and SDI-12, highlighting the robust capability of hybrid models across two case studies. The results indicate that combining WD with ML models can produce more accurate hydrological drought predictions than traditional models.

Nanoparticles Ordering Classification Using Deep Convolutional Neural Networks

Intelligent neural networks are used efficiently for image classification and recognition in various scientific areas. One of the most important of these areas is nanoscience. Researchers are currently seeking to apply various deep learning neural networks models for fast and intelligent prediction and recognition of nanostructures based on scanning electron microscopy images. Models of Deep Convolutional Neural Networks (DCNN) have reached a high accuracy rate in nanoparticles classification and recognition. In fact, the improvement of the classification accuracy strongly relies on the perfect fine-tuning of image data and model parameters and that is what this research has worked for. The aim of this paper is to present a model, specifically the VGG16 convolutional neural network model, for high accurate nanoparticles ordering classification. The model has been used to classify the nanoparticles ordering using a typical dataset of electron microscopy images. In this research, an experiment has been carried out to achieve better accuracy rate in comparison to previously recorded accuracy rates. Data augmentation, modification techniques, and model tuning parameters are applied to excess the ability of the model for classifying the input image to ordered or non-ordered nanoparticles. Compared to the related works, the presented model has outperformed the pervious by achieving an accuracy rate of 97%. In this work, it has been observed that training iterations and balanced training data significantly improve the model performance and enhance the accuracy rate.

Predicting removal of arsenic from groundwater by iron based filters using deep neural network models

Arsenic (As) contamination in drinking water has been highlighted for its environmental significance and potential health implications. Iron-based filters are cost-effective and sustainable solutions for As removal from contaminated water. Applying Machine Learning (ML) models to investigate and optimize As removal using iron-based filters is limited. The present study developed Deep Learning Neural Network (DLNN) models for predicting the removal of As and other contaminants by iron-based filters from groundwater. A small Original Dataset (ODS) consisting of 20 data points and 13 groundwater parameters was obtained from the field performances of 20 individual iron-amended ceramic filters. Cubic-spline interpolation (CSI) expanded the ODS, generating 1600 interpolated data points (IDPs) without duplication. The Bayesian optimization algorithm tuned the model hyper-parameters and IDPs in a Stratified fivefold Cross-Validation (CV) setup trained all the models. The models demonstrated reliable performances with the coefficient of determination (R2) 0.990–0.999 for As, 0.774–0.976 for Iron (Fe), 0.934–0.954 for Phosphorus (P), and 0.878–0.998 for predicting manganese (Mn) in the effluent. Sobol sensitivity analysis revealed that As (total order index (ST) = 0.563), P (ST = 0.441), Eh (ST = 0.712), and Temp (ST = 0.371) are the most sensitive parameters for the removal of As, Fe, P, and Mn. The comprehensive approach, from data expansion through DLNN model development, provides a valuable tool for estimating optimal As removal conditions from groundwater.

Deep Learning and Single-Cell Sequencing Analyses Unveiling Key Molecular Features in the Progression of Carotid Atherosclerotic Plaque.

Rupture of advanced carotid atherosclerotic plaques increases the risk of ischaemic stroke, which has significant global morbidity and mortality rates. However, the specific characteristics of immune cells with dysregulated function and proven biomarkers for the diagnosis of atherosclerotic plaque progression remain poorly characterised. Our study elucidated the role of immune cells and explored diagnostic biomarkers in advanced plaque progression using single-cell RNA sequencing and high-dimensional weighted gene co-expression network analysis. We identified a subcluster of monocytes with significantly increased infiltration in the advanced plaques. Based on the monocyte signature and machine-learning approaches, we accurately distinguished advanced plaques from early plaques, with an area under the curve (AUC) of 0.899 in independent external testing. Using microenvironment cell populations (MCP) counter and non-negative matrix factorisation, we determined the association between monocyte signatures and immune cell infiltration as well as the heterogeneity of the patient. Finally, we constructed a convolutional neural network deep learning model based on gene-immune correlation, which achieved an AUC of 0.933, a sensitivity of 92.3%, and a specificity of 87.5% in independent external testing for diagnosing advanced plaques. Our findings on unique subpopulations of monocytes that contribute to carotid plaque progression are crucial for the development of diagnostic tools for clinical diseases.

МЕТОД КЛАСИФІКАЦІЇ ТЕКСТІВ ЗА ВМІСТОМ ПРОПАГАНДИ НЕЙРОМЕРЕЖЕВИМИ МОДЕЛЯМИ ГЛИБОКОГО НАВЧАННЯ

The method for classifying texts by propaganda content by neural network models of deep learning is proposed, based on combining traditional recurrent neural networks with long-term memory with transformers, which can provide a deeper understanding of sequence and context in text content. The peculiarity of proposed method is that it allows detecting both explicit and hidden propaganda messages, based on combining the capabilities of traditional recurrent neural networks with long-term memory and neural networks-transformers, as well as using the mechanism of training text data augmentation, which allows expand the number of training samples. To evaluate the effectiveness of developed method of classifying texts by the propaganda content using deep learning neural network models, the software implementation was created, which consists of notebooks implemented in the cloud service "Google Colab" and the application for user interaction with the model. Notebooks are used to train the hybrid architecture neural network model and to expand the obtained data set by method of text augmentation. The graphical user interface application developed by Python using the PyCharm development environment. The dataset of more than 25,000 records was created to train the neural network and the corresponding software was developed to investigate the method effectiveness. It was established that with the use of augmentation, better performance is achieved with larger number of epochs, which is explained by the expansion of the training sample, which leads to the need for a larger number of epochs. At the same time, when using augmentation, it was possible to achieve an accuracy of 97.83%, while without augmentation this indicator reached the maximum level of 96.94%. The obtained results demonstrate the ability of the proposed method to effectively classify texts based on the content of propaganda by neural network models of deep learning, and the use of the additional category "suspicious text" made it possible to raise the Precision and Recall indicators, which in turn makes it possible to automate the moderation of texts on the subject of propaganda with errors of no more than 1.83 % for false propaganda detection.

A Plantar Pressure Detection and Gait Analysis System Based on Flexible Triboelectric Pressure Sensor Array and Deep Learning.

Gait detection is essential for the assessment of human health status and early diagnosis of diseases. The current gait analysis systems are bulky, limited in the scope of use, and cause interference with the movement of the measured person. Hence, it is necessary to develop a wearable gait detection system that is soft, breathable, lightweight, and self-powered. Here, a plantar pressure sensor array and gait analysis system based on a flexible triboelectric pressure sensor (FTPS) array is developed. Soft, breathable, and wearable electrospinning nanofiber film with excellent triboelectric properties is used as the plantar pressure sensor, achieving a high sensitivity of 45.1 mVkPa-1 in the range of 40-200 kPa and 19.4 mVkPa-1 in the range of 200-400 kpa. 32 FTPSs are integrated into an intelligent insole, which has the characteristics of soft, easy production, good air permeability, long-time stability, no external power supply, and etc. Based on the long short-term memory artificial neural network deep learning model, the accuracy of gait judgment can reach 94.23%. This work provides a feasible solution for real-time gait detection, which will have potential applications in human health assessment and early diagnosis of disease.

Retraction Note: A novel vessel detection and classification algorithm using a deep learning neural network model with morphological processing (M-DLNN)

Retraction Note: A novel vessel detection and classification algorithm using a deep learning neural network model with morphological processing (M-DLNN)

Multi-branch deep learning neural network prediction model for the development of angular biosensors based on sEMG.

Human gait motion intention recognition is very important for the lower extremity exoskeleton robot to accurately synchronize and respond to the user's natural motion. And motion intention recognition is generally performed through sEMG. Deep learning neural networks perform well in dealing with high-dimensional data and nonlinear relationships such as sEMG, but different deep learning neural networks have their own advantages in dealing with different types of data. Therefore, a multi-branch deep learning neural network, which enables different neural networks to process different feature items, could achieve more accurate and efficient motion intention recognition. The purpose of this study is to 1) Establish a multi-branch deep learning neural network model to achieve accurate gait recognition and effective estimation of joint angles. 2) Quantify the performance of the multi-branch deep learning neural network model in gait recognition and joint angle prediction using sEMG. This study involved the collection of sEMG and plantar pressure data during walking in human subjects. Firstly, the collected signals are filtered and denoised to ensure the quality and reliability of the data. Calculate the time domain features and the frequency domain features to capture the key information of gait. Then, using the sensitivity difference of different structural neural networks to different feature data, a multi-branch deep learning neural network model is developed, in which the extracted features are used as the input of the model. The output of the model includes gait cycle and joint angle, so as to realize the accurate recognition of human gait and the effective estimation of joint angle. The results show that the proposed method has high accuracy in identifying human gait and estimating joint angles. The multi-branch neural network model successfully integrates time-domain and frequency-domain features and provides reliable prediction of gait cycle and joint angle. The highest accuracy of gait recognition is 95.42%, the lowest is 90.11%, and the average is 92.16%. The average error of joint angle estimation is 3.19. This study designed a human walking gait recognition and joint angle prediction model to achieve accurate human lower limb motion intention recognition.The model can be integrated into the sEMG sensor to design a angular biosensors, which can predict the human joint angle in real time.

Inverse design of acoustic metamaterial-based vibration control for offshore wind turbines

This paper presents an inverse design approach for mechanical metamaterial turbines utilising a deep learning algorithm. We first establish a theoretical model for metamaterial turbines using the spectral element method to analyse their vibration characteristics. Subsequently, we predict the vibration transmission properties of these turbines and achieve on-demand inverse design of metastructures through a fully connected deep-learning neural network model. The efficacy of the forward prediction and reverse design network models is validated using an inverse neural network. Our results demonstrate a strong agreement between the predicted and target values, affirming the feasibility of employing deep learning for on-demand meta-turbine design. This intelligent design approach holds promise for expediting and enhancing the design of metamaterials tailored for low-frequency vibration isolation in engineering structures.

Adaptive optimization of thermal energy and information management in intelligent green manufacturing process based on neural network

The study of thermal energy adaptive optimization has important theoretical and practical significance. The deep learning neural network model is used to monitor and analyze the thermal energy data in the manufacturing process in real time. Through the construction of adaptive optimization algorithm, the heat input and output are systematically evaluated and adjusted, and the heat distribution scheme is dynamically optimized according to environmental changes and production needs. At the same time, information management system is introduced to realize data summary, feedback and decision support. The experimental results show that the proposed method can effectively reduce the heat energy loss, optimize the heat energy utilization, and significantly reduce the overall energy consumption compared with traditional management methods. With real-time data updates, the system improves the flexibility and responsiveness of the production process, significantly improving manufacturing efficiency. The thermal energy adaptive optimization method based on neural network provides an effective solution for intelligent green manufacturing, which can not only optimize thermal energy management, but also provide a reference for other resource conservation and environmental protection.

Deep learning-based computer vision in project management: Automating indoor construction progress monitoring

Progress monitoring is crucial for effective project management, particularly in construction projects. The adoption of computer vision with deep learning expedites automation, accuracy, and efficiency in construction progress monitoring by overcoming the challenges of laborious, and error prone manual methods. While there is growing attention on developing computer vision based deep learning models for construction progress monitoring, deployment platforms for project managers are lacking. Using computer vision, this study develops a Mask Recurrent Convolutional Neural Network deep learning model. It utilizes progress images of drywall construction from two indoor construction sites and tests the model on a third indoor site in Sydney, Australia. The model is capable of automated as-built visual detection and work-in-progress measurement. The study also provides an understanding on the deployment process of the deep learning model on a cloud-based platform called Streamlit. By developing a model tailored for automatically quantifying work-in-progress of indoor construction elements and detailing the process of deploying that model on a cloud-based platform, this study significantly advances digitalization of construction project management. Project managers, stand to benefit from these advancements by gaining access to more accurate and automated construction progress monitoring for better decision-making.

A novel approach for automatic classification of macular degeneration OCT images

Age-related macular degeneration (AMD) and diabetic macular edema (DME) are significant causes of blindness worldwide. The prevalence of these diseases is steadily increasing due to population aging. Therefore, early diagnosis and prevention are crucial for effective treatment. Classification of Macular Degeneration OCT Images is a widely used method for assessing retinal lesions. However, there are two main challenges in OCT image classification: incomplete image feature extraction and lack of prominence in important positional features. To address these challenges, we proposed a deep learning neural network model called MSA-Net, which incorporates our proposed multi-scale architecture and spatial attention mechanism. Our multi-scale architecture is based on depthwise separable convolution, which ensures comprehensive feature extraction from multiple scales while minimizing the growth of model parameters. The spatial attention mechanism is aim to highlight the important positional features in the images, which emphasizes the representation of macular region features in OCT images. We test MSA-NET on the NEH dataset and the UCSD dataset, performing three-class (CNV, DURSEN, and NORMAL) and four-class (CNV, DURSEN, DME, and NORMAL) classification tasks. On the NEH dataset, the accuracy, sensitivity, and specificity are 98.1%, 97.9%, and 98.0%, respectively. After fine-tuning on the UCSD dataset, the accuracy, sensitivity, and specificity are 96.7%, 96.7%, and 98.9%, respectively. Experimental results demonstrate the excellent classification performance and generalization ability of our model compared to previous models and recent well-known OCT classification models, establishing it as a highly competitive intelligence classification approach in the field of macular degeneration.

Parking search identification in vehicle GPS traces

The challenge of “cruising for parking” in urban areas has long been a subject of study, but existing research often relies on biased surveys or arbitrary assumptions in the absence of ground truth data. This paper addresses these gaps by introducing the first-ever collection of ground truth data on parking search durations gathered through a self-developed app. The dataset encompasses more than 3500 journeys collected in Germany, with approximately two-thirds of them ending in Frankfurt am Main. Utilizing this unique dataset, we developed a deep learning neural network model that accurately identifies parking search routes in GPS data and predicts search duration. Our model outperforms existing parking search identification models proposed in previous studies. The model’s efficacy is further evaluated on an independent park-and-visit dataset and then applied to a large-scale dataset from Frankfurt/Germany. This generates the first reliable statistics on parking search durations and reveals key insights about parking search patterns in this city. Notably, the predicted mean parking search duration from this extensive dataset, comprising over 860,000 journeys, is approximately 1.5 min. This work not only advances the field by providing a new data collection methodology and a superior predictive model but also offers a reusable framework that can be applied to other cities and datasets for broader urban mobility insights.

Retraction Note: Optimized deep learning neural network model for doubly fed induction generator in wind energy conversion systems

Retraction Note: Optimized deep learning neural network model for doubly fed induction generator in wind energy conversion systems

Pupillometry as a biomarker of postural control: Deep-learning models reveal side-specific pupillary responses to increased intensity of balance tasks.

Pupillometry has been used in the studies of postural control to assess cognitive load during dual tasks, but its response to increased balance task intensity has not been investigated. Furthermore, it is unknown whether side-specific changes in pupil diameter occur with more demanding balance tasks providing additional insights into postural control. The two aims of this study were to analyze differences in steady-state pupil diameter between balance tasks with increased intensity and to determine whether there are side-specific changes. Forty-eight healthy subjects performed parallel and left and right one-legged stances on a force plate with and without foam with right and left pupil diameters measured with a mobile infrared eye-tracker. Differences between balance tasks in parameters (average pupil diameter of each eye, average of both pupil diameters and the difference between the left and right pupil diameter) were analyzed using a two-way repeated measures analysis of variance, and deep learning neural network models were used to investigate how pupillometry predicted each balance task. The pupil diameter of the left eye, the average pupil diameter of both eyes and the difference in pupil diameters increased statistically significantly from simpler to more demanding balance tasks, with this being more pronounced for the left eye. The deep learning neural network models revealed side-specific changes in pupil diameter with more demanding balance tasks. This study confirms pupillary responses to increased intensity of balance task and indicates side-specific pupil responses that could be related to task-specific involvement of higher levels of postural control.

Decoding dynamic visual scenes across the brain hierarchy.

Understanding the computational mechanisms that underlie the encoding and decoding of environmental stimuli is a crucial investigation in neuroscience. Central to this pursuit is the exploration of how the brain represents visual information across its hierarchical architecture. A prominent challenge resides in discerning the neural underpinnings of the processing of dynamic natural visual scenes. Although considerable research efforts have been made to characterize individual components of the visual pathway, a systematic understanding of the distinctive neural coding associated with visual stimuli, as they traverse this hierarchical landscape, remains elusive. In this study, we leverage the comprehensive Allen Visual Coding-Neuropixels dataset and utilize the capabilities of deep learning neural network models to study neural coding in response to dynamic natural visual scenes across an expansive array of brain regions. Our study reveals that our decoding model adeptly deciphers visual scenes from neural spiking patterns exhibited within each distinct brain area. A compelling observation arises from the comparative analysis of decoding performances, which manifests as a notable encoding proficiency within the visual cortex and subcortical nuclei, in contrast to a relatively reduced encoding activity within hippocampal neurons. Strikingly, our results unveil a robust correlation between our decoding metrics and well-established anatomical and functional hierarchy indexes. These findings corroborate existing knowledge in visual coding related to artificial visual stimuli and illuminate the functional role of these deeper brain regions using dynamic stimuli. Consequently, our results suggest a novel perspective on the utility of decoding neural network models as a metric for quantifying the encoding quality of dynamic natural visual scenes represented by neural responses, thereby advancing our comprehension of visual coding within the complex hierarchy of the brain.

Estimating three-dimensional foot bone kinematics from skin markers using a deep learning neural network model

The human foot is a complex structure comprising 26 bones, whose coordinated movements facilitate proper deformation of the foot, ensuring stable and efficient locomotion. Despite their critical role, the kinematics of foot bones during movement remain largely unexplored, primarily due to the absence of non-invasive methods for measuring foot bone kinematics. This study addresses this gap by proposing a neural network model for estimating foot bone movements using surface markers. To establish a mapping between the positions and orientations of the foot bones and 41 skin markers attached on the human foot, computed tomography scans of the foot with the markers were obtained with eleven healthy adults and thirteen cadaver specimens in different foot postures. The neural network architecture comprises four layers, with input and output layers containing the 41 marker positions and the positions and orientations of the nine foot bones, respectively. The mean errors between estimated and true foot bone position and orientation were 0.5 mm and 0.6 degrees, respectively, indicating that the neural network can provide 3D kinematics of the foot bones with sufficient accuracy in a non-invasive manner, thereby contributing to a better understanding of foot function and the pathogenetic mechanisms underlying foot disorders.

Predicting Structural Temperature of Ancient City Walls: A Case Study Using Ambient Temperature and Deep Learning

ABSTRACT Accurate prediction of the structural temperature field is required for the performance assessment of engineering structures and for maintaining structural safety. However, there are complex time-lag effects between ambient temperature and structural temperature. It is difficult to accurately describe and predict the structural temperature using traditional linear and nonlinear fitting methods. Hence, this study uses the advantages of gated recurrent unit (GRU) neural networks in dealing with complex nonlinear mapping issues, further considering solar radiation and developing a structural temperature prediction framework using ambient temperature and the deep learning model. The framework is applied in structural temperature prediction for an ancient city wall in China. The solar altitude angle at the location of the city wall is calculated, and the input and output structures of the deep learning neural network model are optimized. In the long-term prediction of the structural temperature of the city wall, the root mean square error (RMSE) of the GRU model is less than 0.6°C, which solves the problem of low accuracy caused by time-lag effects.

Threshold Active Learning Approach for Physical Violence Detection on Images Obtained from Video (Frame-Level) Using Pre-Trained Deep Learning Neural Network Models

Threshold Active Learning Approach for Physical Violence Detection on Images Obtained from Video (Frame-Level) Using Pre-Trained Deep Learning Neural Network Models

Real time feedback and E-learning intelligent entertainment experience in computer English communication based on deep learning

Traditional E-learning usually lacks real-time feedback and interactivity, which can not meet the needs of students’ personalized learning. Computer English communication is an important aspect of cultivating students’ language communication ability, which has a positive impact on students’ learning results. In order to realize the real-time feedback of computer English communication and E-learning intelligent entertainment experience, this study stimulates students’ learning interest and improves their learning effect by providing real-time feedback and personalized learning content. With the development of computer network technology, E-learning English platforms can provide students with intelligent entertainment experiences and real-time learning feedback. This article analyzes the real-time feedback and E-learning intelligent entertainment experience of computer English communication based on deep learning. Firstly, an in-depth analysis was conducted on the characteristics of English communication. English communication has specific grammatical structures and professional terms, which require quick and accurate understanding and expression of information. On this basis, a training dataset was constructed, preprocessed and annotated, cleaned to remove irrelevant information and noise, and then corresponding labels were added to each data sample. Subsequently, the constructed dataset was used to optimize the deep learning and recurrent neural network models, and the model parameters were optimized using a backpropagation algorithm. The experimental results show that the method designed in this article has higher accuracy and real-time performance, can timely identify learners’ problems and provide personalized feedback, accurately evaluate learners’ communication ability, and provide targeted feedback.