Model Of Deep Structure Research Articles

Deep interval type-2 generalized fuzzy hyperbolic tangent system for nonlinear regression prediction

Recently, due to the rapid rise of artificial intelligence (AI), considerable progress has been made in the field of nonlinear regression prediction. However, many existing methods suffer from the issues of rule and parameter explosion and poor accuracy, particularly for high-dimensional data with uncertainty. To address these limitations, this paper proposes a deep interval type-2 generalized fuzzy hyperbolic tangent system (DIT2GFHS). First, a novel neural network-based implementation of the interval type-2 fuzzy generalized fuzzy hyperbolic tangent system (IT2GFHS) is introduced to improve the efficiency of system parameter updates and optimization. Then, using a hierarchical and block-based framework, multiple IT2GFHSs are stacked layer by layer from bottom to top to construct the DIT2GFHS, with each layer’s fuzzy subsystems being independent of the others. Additionally, DIT2GFHS incorporates optimization algorithms and the Adam optimizer for training, thereby avoiding the tedious manual parameter tuning process. The detailed analysis of the construction manner and internal mechanisms for DIT2GFHS indicates that it features a reduced number of parameters, a transparent and clear structure, strong capability in handling uncertainty, and favorable accuracy. Notably, the small number of parameters and the explicit structure reduce computational and hardware burdens while maintaining interpretability. Finally, extensive experimental studies on both relatively low-dimensional and high-dimensional datasets are conducted. The results demonstrate that DIT2GFHS achieves excellent performance with fewer parameters compared to many deep-structured models, including deep fuzzy systems and deep learning models. This highlights its potential impact in addressing practical nonlinear regression problems.

Exploration of the Subsurface Three-Dimensional Structure in Rare Earth Ore Areas Using Electrical Resistivity Tomography: A Case Study in Changting, Fujian, China

The development of fracture zones (broken zones) and underground karst rivers in underlying granite can significantly reduce the recovery rate of ion-adsorption-type rare earth ores. Additionally, leaching solutions flowing along unfavorable geological formations can lead to environmental pollution. Therefore, investigating the development of fracture zones (leakage channels) in granite basements is of great significance. In Changting, Fujian, China, several methods have been used in exploration areas (C1 and C2) to study the characteristics of rare ores. This study has focused on the stratigraphic and structural characteristics of the C2 exploration area. Twelve exploration profiles were designed to collect data using electrical resistivity tomography, and a deep electrical structure model of the study area was obtained through inverse calculations. The results indicated that the exploration profiles effectively delineated the thickness of the weathered granite layer and the spatial distribution characteristics of the deep-seated fault structures, which were consistent with the drilling results within the study area. These findings provide important reference materials for the assessment of ion-adsorption-type rare earth ore reserves, blocking leakage channels, and the layout of recovery tunnels.

Chromosome analysis using a hybrid deep CNN and structural feature-based grouping model

Chromosome analysis using a hybrid deep CNN and structural feature-based grouping model

Generalizing deep learning electronic structure calculation to the plane-wave basis.

Deep neural networks capable of representing the density functional theory (DFT) Hamiltonian as a function of material structure hold great promise for revolutionizing future electronic structure calculations. However, a notable limitation of previous neural networks is their compatibility solely with the atomic-orbital (AO) basis, excluding the widely used plane-wave (PW) basis. Here we overcome this critical limitation by proposing an accurate and efficient real-space reconstruction method for directly computing AO Hamiltonian matrices from PW DFT results. The reconstruction method is orders of magnitude faster than traditional projection-based methods to convert PW results to the AO basis, and the reconstructed Hamiltonian matrices can faithfully reproduce the PW electronic structure, thus bridging the longstanding gap between the AO basis deep learning electronic structure approach and PW DFT. Advantages of the PW methods, such as high accuracy, high flexibility and wide applicability, thus can be all integrated into deep learning electronic structure methods without sacrificing these methods' inherent benefits. This allows for the construction of large-scale and high-fidelity training datasets with the help of PW DFT results towards the development of precise and broadly applicable deep learning electronic structure models.

AI-Personalized Elegance: Optimizing Your Appearance with Smart Hairstyle Recommendations

Many machine learning algorithms have been introduced to solve different types of problems. Recently, many of these algorithms have been applied to deep architecture models and showed very impressive performances. In general, deep architecture models suffer from the over-fitting problem when there is a small number of training data. In this article the attempt is made to remedy this problem in deep architecture with regularization techniques including overlap pooling and flipped image augmentation and dropout; the authors also compared a deep structure model (convolutional neural network (CNN)) with shallow structure models (support vector machine and artificial neural network with one hidden layer) on a small dataset. It was statistically confirmed that the shallow models achieved better performance than the deep model that did not use a regularization technique. Faces represent complex multidimensional meaningful visual stimuli and developing a computational model for face recognition is difficult. The authors present a hybrid neural-network solution which compares favorably with other methods. Keyword Hair style recommendation; Face recognition; Machine learning; Software Development

Recommendation System for Hairstyle Based on Face Recognition Using AI and Machine Learning

Many machine learning algorithms have been introduced to solve different types of problems. Recently, many of these algorithms have been applied to deep architecture models and showed very impressive performances. In general, deep architecture models suffer from the over-fitting problem when there is a small number of training data. In this article the attempt is made to remedy this problem in deep architecture with regularization techniques including overlap pooling and flipped image augmentation and dropout; the authors also compared a deep structure model (convolutional neural network (CNN)) with shallow structure models (support vector machine and artificial neural network with one hidden layer) on a small dataset. It was statistically confirmed that the shallow models achieved better performance than the deep model that did not use a regularization technique. Faces represent complex multidimensional meaningful visual stimuli and developing a computational model for face recognition is difficult. The authors present a hybrid neural-network solution which compares favorably with other methods.

ГЛУБИННАЯ МОДЕЛЬ ЛИТОСФЕРЫ ВДОЛЬ ГЕОТРАНСЕКТА Г. СПАССК-ДАЛЬНИЙ – БУХ. ЗЕРКАЛЬНАЯ

The possibility is shown of joint interpretation of seismic, density, magnetic and geoelectric models of the lithosphere deep structure along the Spassk-Dalniy – Zerkalnaya Bay geotraverse. Seismic and density boundaries form the main structural framework of the integrated model of the lithosphere. Magnetic heterogeneities map the elements associated with magmatism. The electrical model reflects the most recent processes of matter redistribution. The resulting integrated geophysical model demonstrated that for the terranes identified on the surface and most of the faults separating them the structural style is well expressed only within the upper and middle parts of the earth’s crust to a depth of 10-20 km. The lithosphere of the Khanka superterrane retains its structure both in the earth’s crust and in the mantle. Structures of the crust and upper mantle of the Sikhote-Alin orogenic belt are different and associated with each other through highly conductive areas and zones.

Deep structure and formation model of the southernmost Tanlu fault Zone, eastern China: Constrained from magnetotelluric imaging

Deep structure and formation model of the southernmost Tanlu fault Zone, eastern China: Constrained from magnetotelluric imaging

Extracting fact-condition relation from geological papers via deep structured semantic model with multi-grained representation

The fact-condition statement plays a significant role in the geological papers, where geological theory or phenomenon as a fact is constrained by its precondition. This constraint relation conveys a lot of key information in geological papers, but it has been ignored in most of studies on the information extraction. Although the rule-based algorithms have been proposed in the previous studies to extract the relationship between facts and conditions, but their low accuracy limit usability. Therefore, this paper introduces a series of mechanisms and methods to improve the extraction accuracy. We firstly utilize three kinds of pooling for extracting the semantic features of fact-condition tuples to find that balanced semantic representations can more accurately reflect their relations. In addition, semantic correlation between facts and conditions is also designed to mine their relations via the measurement of semantic similarity or semantic distance. Based on the above, the Deep Structured Semantic Model with Multi-Grained Representation (MGR-DSSM) is proposed. In this model, the Deep Structured Semantic Model (DSSM) is utilized two individual projections for denoising semantic correlation between facts and conditions, while the Multi-Grained Representation (MGR) is designed for encoding their semantic correlation at multiple granularities. Furthermore, the linear MGR-DSSM with SciBERT achieves the best result with 70.41% of accuracy and 74.55% of F1 score, obviously outperforming other baseline models. Finally, the linear MGR-DSSM with SciBERT is adopted to extract super relation from 722 geological paper abstracts, and the geological knowledge graph with fact-condition statement is built. With more accurate relation between fact and condition, the information validity of geological knowledge graph is enhanced.

Medical Image Segmentation Based on U-Net

Traditional statistical methods, although having a solid theoretical foundation, have been challenged in terms of their efficiency as well as their generalization ability in the face of the ever-increasing amount of massive data. With the rise of deep learning in recent years, the use of new tools such as convolutional neural networks to get information from data has become a new option. In particular, in the field of imaging, segmentation of medical images is important for tasks such as determining the type of disease and the location of lesions, which are excellent application areas for deep learning. U-Net is a particularly important deep model structure with good results for segmentation of medical images. However, there is a lack of discussions on the application of U-Net in the clinical field. In this paper, we introduce traditional image segmentation methods and U-Net, analyze the advantages of deep learning techniques in the field of image segmentation. In addition, we applied U-Net to the problem of cell segmentation and segmentation of covid-19 CT images, showing the potential of U-Net for clinical applications.

Predicting near-term glaucoma progression: An artificial intelligence approach using clinical free-text notes and data from electronic health records.

The purpose of this study was to develop a model to predict whether or not glaucoma will progress to the point of requiring surgery within the following year, using data from electronic health records (EHRs), including both structured data and free-text progress notes. A cohort of adult glaucoma patients was identified from the EHR at Stanford University between 2008 and 2020, with data including free-text clinical notes, demographics, diagnosis codes, prior surgeries, and clinical information, including intraocular pressure, visual acuity, and central corneal thickness. Words from patients' notes were mapped to ophthalmology domain-specific neural word embeddings. Word embeddings and structured clinical data were combined as inputs to deep learning models to predict whether a patient would undergo glaucoma surgery in the following 12 months using the previous 4-12 months of clinical data. We also evaluated models using only structured data inputs (regression-, tree-, and deep-learning-based models) and models using only text inputs. Of the 3,469 glaucoma patients included in our cohort, 26% underwent surgery. The baseline penalized logistic regression model achieved an area under the receiver operating curve (AUC) of 0.873 and F1 score of 0.750, compared with the best tree-based model (random forest, AUC 0.876; F1 0.746), the deep learning structured features model (AUC 0.885; F1 0.757), the deep learning clinical free-text features model (AUC 0.767; F1 0.536), and the deep learning model with both the structured clinical features and free-text features (AUC 0.899; F1 0.745). Fusion models combining text and EHR structured data successfully and accurately predicted glaucoma progression to surgery. Future research incorporating imaging data could further optimize this predictive approach and be translated into clinical decision support tools.

Are Deep Learning Structural Models Sufficiently Accurate for Virtual Screening? Application of Docking Algorithms to AlphaFold2 Predicted Structures.

Machine learning-based protein structure prediction algorithms, such as RosettaFold and AlphaFold2, have greatly impacted the structural biology field, arousing a fair amount of discussion around their potential role in drug discovery. While there are few preliminary studies addressing the usage of these models in virtual screening, none of them focus on the prospect of hit-finding in a real-world virtual screen with a model based on low prior structural information. In order to address this, we have developed an AlphaFold2 version where we exclude all structural templates with more than 30% sequence identity from the model-building process. In a previous study, we used those models in conjunction with state-of-the-art free energy perturbation methods and demonstrated that it is possible to obtain quantitatively accurate results. In this work, we focus on using these structures in rigid receptor-ligand docking studies. Our results indicate that using out-of-the-box Alphafold2 models is not an ideal scenario for virtual screening campaigns; in fact, we strongly recommend to include some post-processing modeling to drive the binding site into a more realistic holo model.

A classification model for detection of ductal carcinoma in situ by Fourier transform infrared spectroscopy based on deep structured semantic model

At present, deep learning is widely used in spectral data processing. Deep learning requires a large amount of data for training, while the collection of biological serum spectra is limited by sample numbers and labor costs, so it is impractical to obtain a large amount of serum spectral data for disease detection. In this study, we propose a spectral classification model based on the deep structured semantic model (DSSM) and successfully apply it to Fourier Transform Infrared (FT-IR) spectroscopy for ductal carcinoma in situ (DCIS) detection. Compared with the traditional deep learning model, we match the spectral data into positive and negative pairs according to whether the spectra are from the same category. The DSSM structure is constructed by extracting features according to the spectral similarity of spectra pairs. This new construction model increases the data amount used for model training and reduces the dimension of spectral data. Firstly, the FT-IR spectra are paired. The spectra pairs are labeled as positive pairs if they come from the same category, and the spectra pairs are labeled as negative pairs if they come from different categories. Secondly, two spectra in each spectra pair are put into two deep neural networks of the DSSM structure separately. Then the spectral similarity between the output feature maps of two deep neural networks is calculated. The DSSM structure is trained by maximizing the conditional likelihood of the spectra pairs from the same category. Thirdly, after the training of DSSM is done, the training set and testing set are input into two deep neural networks separately. The output feature maps of the training set are put into the reference library. Lastly, the k-nearest neighbor (KNN) model is used for classification according to Euclidean distances between the output feature map of each unknown sample to the reference library. The category of the unknown sample is judged according to the categories of k nearest samples. We also use principal component analysis (PCA) to reduce dimension for comparison. The accuracies of the KNN model, principal component analysis-k nearest neighbor (PCA-KNN) model, and deep structured semantic model-k nearest neighbor (DSSM-KNN) model are 78.8%, 72.7%, and 97.0%, which proves that our proposed model has higher accuracy.

Construction and application analysis of thermal conductivity model of deep thermal storage pore structure

In the process of geothermal energy exploitation and utilization, effective heat extraction, natural recovery and other key issues are affected and restricted by the thermal conductivity process of geothermal reservoirs, and the relevant thermal conductivity model research is not very comprehensive at present. In this paper, the deep heat storage in pore structure is divided into development zone, wave zone and original zone according to their thermal conductivity characteristics. Based on the representative elementary volume description analysis method, the thermal conductivity analysis model of pore structure of deep heat storage is established, including simplified thermal conductivity model and fine thermal conductivity model. Taking granite as an example, numerical calculation was carried out to analyze the effects of porosity, impurity content, water content and channel composition coefficient on heat storage and thermal conductivity. The model established in this paper lays a foundation for controlling thermal storage and thermal conductivity mechanism, accurately analyzing thermal conductivity characteristics, reserve estimation and mining dynamic changes.

The Efficacy of Pretreatment 18F-FDG PET-CT-Based Deep Learning Network Structure to Predict Survival in Nasopharyngeal Carcinoma.

Previous studies have shown that the 5-year survival rates of patients with nasopharyngeal carcinoma (NPC) were still not ideal despite great improvement in NPC treatments. To achieve individualized treatment of NPC, we have been looking for novel models to predict the prognosis of patients with NPC. The objective of this study was to use a novel deep learning network structural model to predict the prognosis of patients with NPC and to compare it with the traditional PET-CT model combining metabolic parameters and clinical factors. A total of 173 patients were admitted to 2 institutions between July 2014 and April 2020 for the retrospective study; each received a PET-CT scan before treatment. The least absolute shrinkage and selection operator (LASSO) was employed to select some features, including SUVpeak-P, T3, age, stage II, MTV-P, N1, stage III and pathological type, which were associated with overall survival (OS) of patients. We constructed 2 survival prediction models: an improved optimized adaptive multimodal task (a 3D Coordinate Attention Convolutional Autoencoder and an uncertainty-based jointly Optimizing Cox Model, CACA-UOCM for short) and a clinical model. The predictive power of these models was assessed using the Harrell Consistency Index (C index). Overall survival of patients with NPC was compared by Kaplan-Meier and Log-rank tests. The results showed that CACA-UOCM model could estimate OS (C index, 0.779 for training, 0.774 for validation, and 0.819 for testing) and divide patients into low and high mortality risk groups, which were significantly associated with OS (P < .001). However, the C-index of the model based only on clinical variables was only 0.42. The deep learning network model based on 18F-FDG PET/CT can serve as a reliable and powerful predictive tool for NPC and provide therapeutic strategies for individual treatment.

A Deep Structural Model for Empirical Asset Pricing

A Deep Structural Model for Empirical Asset Pricing

Two Approaches to Visual Relations: Deep Learning versus Structural Models

Two Approaches to Visual Relations: Deep Learning versus Structural Models

Are Deep Learning Structural Models Sufficiently Accurate for Free-Energy Calculations? Application of FEP+ to AlphaFold2-Predicted Structures.

The availability of AlphaFold2 has led to great excitement in the scientific community─particularly among drug hunters─due to the ability of the algorithm to predict protein structures with high accuracy. However, beyond globally accurate protein structure prediction, it remains to be determined whether ligand binding sites are predicted with sufficient accuracy in these structures to be useful in supporting computationally driven drug discovery programs. We explored this question by performing free-energy perturbation (FEP) calculations on a set of well-studied protein-ligand complexes, where AlphaFold2 predictions were performed by removing all templates with >30% identity to the target protein from the training set. We observed that in most cases, the ΔΔG values for ligand transformations calculated with FEP, using these prospective AlphaFold2 structures, were comparable in accuracy to the corresponding calculations previously carried out using crystal structures. We conclude that under the right circumstances, AlphaFold2-modeled structures are accurate enough to be used by physics-based methods such as FEP in typical lead optimization stages of a drug discovery program.

Retraction Note to: An improved hybridized deep structured model for accurate video event recognition

Retraction Note to: An improved hybridized deep structured model for accurate video event recognition

Linking Exploits from the Dark Web to Known Vulnerabilities for Proactive Cyber Threat Intelligence: An Attention-Based Deep Structured Semantic Model

Black hat hackers use malicious exploits to circumvent security controls and take advantage of system vulnerabilities worldwide, costing the global economy over $450 billion annually. While many organizations are increasingly turning to cyber threat intelligence (CTI) to help prioritize their vulnerabilities, extant CTI processes are often criticized as being reactive to known exploits. One promising data source that can help develop proactive CTI is the vast and ever-evolving Dark Web. In this study, we adopted the computational design science paradigm to design a novel deep learning (DL)- based exploit-vulnerability attention deep structured semantic model (EVA-DSSM) that includes bidirectional processing and attention mechanisms to automatically link exploits from the Dark Web to vulnerabilities. We also devised a novel device vulnerability severity metric (DVSM) that incorporates the exploit post date and vulnerability severity to help cybersecurity professionals with their device prioritization and risk management efforts. We rigorously evaluated the EVA-DSSM against state-of-theart non-DL and DL-based methods for short text matching on 52,590 exploit-vulnerability linkages across four testbeds: web application, remote, local, and denial of service. Results of these evaluations indicate that the proposed EVA-DSSM achieves precision at 1 scores 20% - 41% higher than non-DL approaches and 4% - 10% higher than DL-based approaches. We demonstrated the EVA-DSSM’s and DVSM’s practical utility with two CTI case studies: openly accessible systems in the top eight U.S. hospitals and over 20,000 Supervisory Control and Data Acquisition (SCADA) systems worldwide. A complementary user evaluation of the case study results indicated that 45 cybersecurity professionals found the EVADSSM and DVSM results more useful for exploit-vulnerability linking and risk prioritization activities than those produced by prevailing approaches. Given the rising cost of cyberattacks, the EVA-DSSM and DVSM have important implications for analysts in security operations centers, incident response teams, and cybersecurity vendors.