High-dimensional Space Research Articles

A review of unsupervised learning in astronomy

This review summarises popular unsupervised learning methods, and gives an overview of their past, current, and future uses in astronomy. Unsupervised learning aims to organise the information content of a dataset, in such a way that knowledge can be extracted. Traditionally this has been achieved through dimensionality reduction techniques that aid the ranking of a dataset, for example through principal component analysis or by using auto-encoders, or simpler visualisation of a high dimensional space, for example through the use of a self organising map. Other desirable properties of unsupervised learning include the identification of clusters, i.e. groups of similar objects, which has traditionally been achieved by the k-means algorithm and more recently through density-based clustering such as HDBSCAN. More recently, complex frameworks have emerged, that chain together dimensionality reduction and clustering methods. However, no dataset is fully unknown. Thus, nowadays a lot of research has been directed towards self-supervised and semi-supervised methods that stand to gain from both supervised and unsupervised learning.

Multi-Class Network Anomaly Detection Using Machine Learning Techniques

Computer networks rely on Intrusion Detection Systems (IDSs) and Intrusion Prevention Systems (IPSs) to ensure the security, reliability, and availability of an organization. In recent years, various approaches were developed and implemented to create effective IDSs and IPSs. This paper specifically focuses on IDSs that utilize Machine Learning (ML) techniques for improved accuracy. ML-based IDSs have verified to be successful in discovering network attacks. However, their performance tends to decline when dealing with high-dimensional data spaces. It is essential to develop a suitable feature extraction strategy that could identify and remove irrelevant features that do not significantly classification process to address this issue. Additionally, many ML-based IDSs exhibit high false positive rates and poor detection accuracy when trained on unbalanced datasets. In this study, we analyze the UNSW-NB15 IDS, which will serve as the training and testing data for our models. In order to reduce the feature space and improve the efficiency of our analysis, we leverage a filter-based feature reduction method utilizing the Pearson correlation coefficient algorithm. By identifying and selecting only the most relevant features, we are able to streamline our dataset and focus on the variables that have the highest impact on our analysis. This approach not only reduces computational complexity but also improves the interpretability of our results by eliminating unnecessary noise from the data. After applying the feature reduction technique, we proceed to implement a range of machine learning methods to perform our classification task. These include well-known algorithms such as Stacking, Extra Trees, Multi-Layer Perceptron, XGBoost, K-Nearest Neighbors, Logistic Regression, Naïve Bayes, Support Vector Machine, Random Forest, and Decision Tree. By employing a diverse set of algorithms, we are able to explore different modeling approaches and evaluate their effectiveness in accurately classifying the various types of assaults. In order to assess the performance of our classification models, we utilize a range of specialized evaluation metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), R2-Score, Mean Squared Error (MSE), Precision, F1-Score, Recall, and Accuracy. These metrics provide us with a comprehensive understanding of how well our models are performing across different dimensions, including the accuracy of predictions, the level of precision in classifying different assault types, and the overall goodness-of-fit of our models. By considering multiple evaluation metrics, we are able to gain a more nuanced understanding of the strengths and weaknesses of each algorithm and make informed decisions about their suitability for our classification task. These metrics deliver a complete evaluation of the classifiers’ effectiveness in detecting community intrusions.

Deep Causal Reasoning for Recommendations

Traditional recommender systems aim to estimate a user’s rating to an item based on observed ratings from the population. As with all observational studies, hidden confounders, which are factors that affect both item exposures and user ratings, lead to a systematic bias in the estimation. Consequently, causal inference has been introduced in recommendations to address the influence of unobserved confounders. Observing that confounders in recommendations are usually shared among items and are therefore multi-cause confounders, we model the recommendation as a multi-cause multi-outcome (MCMO) inference problem. Specifically, to remedy the confounding bias, we estimate user-specific latent variables that render the item exposures independent Bernoulli trials. The generative distribution is parameterized by a DNN with factorized logistic likelihood and the intractable posteriors are estimated by variational inference. Controlling these factors as substitute confounders, under mild assumptions, can eliminate the bias incurred by multi-cause confounders. Furthermore, we show that MCMO modeling may lead to high variance due to scarce observations associated with the high-dimensional treatment space. Therefore, we theoretically demonstrate that controlling user features as pre-treatment variables can substantially improve sample efficiency and alleviate overfitting. Empirical studies on both simulated and real-world datasets demonstrate that the proposed deep causal recommender shows more robustness to unobserved confounders than state-of-the-art causal recommenders. Codes and datasets are released at https://github.com/yaochenzhu/Deep-Deconf.

Decision-making Support Platform and Security Design for Rural Leisure Tour Industry based on SEA Method and SVR Model

An accurate short-term passenger flow forecast of rural tourism can avoid accidents as much as possible. However, the short-term passenger flow of rural leisure tourism shows nonlinear, seasonal, random, and other complex characteristics. Meanwhile, the traditional forecasting methods are often difficult to achieve accurate forecasting. Therefore, this study now used the nonlinear mapping function in the support vector regression to convert the passenger traffic training sample into a high-dimensional feature space and established a linear decision function. Then the influence of periodicity on the prediction effect through seasonal index adjustment was reduced. Finally, event triggering combined with core embedding technology for tamper-proof detection was adopted to improve the security of the platform. The results showed that the minimum absolute error of prediction with improved SVM model was 0.27% compared with traditional model and autoregressive integrated moving average model. After the introduction of the Internet search factor, the traffic prediction result was more accurate, which was 0.0425 smaller than that without the introduction of the Internet search factor. When the concurrency was less than 100 times/s, the average response time difference before and after adding the core embedded program was small, indicating that the security of page tampering technology was high. This research method can effectively predict the passenger flow of rural leisure tourism industry and ensure the safety of the platform.

Local Contrast Learning for One-Shot Learning

Learning a deep model from small data is an opening and challenging problem. In high-dimensional spaces, few samples only occupy an extremely small portion of the space, often exhibiting sparsity issues. Classifying in this globally sparse sample space poses significant challenges. However, by using a single sample category as a reference object for comparing and recognizing other samples, it is possible to construct a local space. Conducting contrastive learning in this local space can overcome the sparsity issue of a few samples. Based on this insight, we proposed a novel deep learning approach named Local Contrast Learning (LCL). This is analogous to a key insight into human cognitive behavior, where humans identify the objects in a specific context by contrasting them with the objects in that context or from their memory. LCL is used to train a deep model that can contrast the recognized sample with a couple of contrastive samples that are randomly drawn and shuffled. On a one-shot classification task on Omniglot, the deep model-based LCL with 86 layers and 1.94 million parameters, which was trained on a tiny dataset with only 60 classes and 20 samples per class, achieved an accuracy of 98.95%. Furthermore, it achieved an accuracy of 99.24% at 156 classes and 20 samples per class. LCL is a fundamental idea that can be applied to alleviate the parametric model’s overfitting resulting from a lack of training samples.

Two-stage many-objective evolutionary algorithm: enhanced dominance relations and control mechanisms for separated balance

Although the multiobjective evolutionary algorithms (MOEAs) have been proved to bring promising prospects for solving multiobjective optimization problems (MOPs), the performance of the algorithm deteriorates sharply in high-dimensional objective space due to the weak selection pressure and the unregulated balance, which is caused by the increase of objective space dimension. Some current MOEAs with two-stage strategy (TS) strive to address above issues by dividing the evolutionary process into two independent stages, in which convergence and diversity are handled separately within successive generations of different stages. However, TS-MOEAs have some weaknesses, such as sensitivity to stage division, and incomplete separation of convergence and diversity. In this paper, TS/KW-MaOEA is proposed for solving many-objective optimization problems (MaOPs), which keeps TS as the central and equips a perfect control mechanism for separated balance. More specifically, TS/KW-MaOEA can automatically adjust the balance trend and provide appropriate selection pressure for MaOPs according to the Kondratiev wave (KW) search model and the objective space dimension. To verify the effectiveness of the proposed algorithm, a series of experiments are carried out against seven state-of-the-art many-objective optimization algorithms on 15 benchmark problems with up to 30 objectives. Experimental results indicate that the proposed algorithm is highly competitive against peer competitors.

A strategy for high-entropy copper alloys composition design assisted by deep learning based on data reconstruction and network structure optimization

Complex mapping relationships between high-entropy alloy compositions and performances struggle to precisely elucidate by traditional machine learning models, hindering the accurate and efficient design of high-performance alloys. In this work, a novel alloy design strategy combined self-decision deep neural network, data reconstruction with network structure optimization was proposed, which effectively enhanced the model's ability to predict the mapping relationships between high-dimensional composition spaces and mechanical properties of alloy. Compared to other machine learning methods, significantly improves model prediction accuracy (hardness model: 97.98%; strength model: 94.40%). Through above model, the mechanical properties of 308 new (CuNiMn)-X high-entropy copper alloys was studied added other elements such as Al, Ti, Cr, and Fe, which designed and produced a novel (CuNiMn)60Al20Cr20 alloy with high hardness of 474 HV, high compressive strength of 2322 MPa, and high fracture strain of 25.20%. The primary factors influencing alloy performance and their respective thresholds were also quantitatively revealed (hardness: electronegativity deviation (0.02, 0.1) and nuclear charge deviation (0, 0.25); compressive strength: mean nuclear charge (25, 30) and mean atomic radius (134 p.m.)). These findings provide a new perspective and approach for the design and mechanism understanding of high-performance alloys with complex compositions.

Happy people are always similar: The evidence from brain morphological and functional inter-subject correlations

A fundamental question in the study of happiness is whether there is neural evidence to support a well-known hypothesis that happy people are always similar while unfortunate people have their own misfortunes. To investigate this, we employed several happiness-related questionnaires to identify potential components of happiness, and further investigated and confirmed their associations with personality, mood, aggressive behaviors, and amygdala reactivity to fearful faces within a substantial sample size of college students (n = 570). Additionally, we examined the functional and morphological similarities and differences among happy individuals using the inter-subject representational similarity analysis (IS-RSA). IS-RSA emphasizes the geometric properties in a high-dimensional space constructed by brain or behavioral patterns and focuses on individual subjects. Our behavioral findings unveiled two factors of happiness: individual and social, both of which mediated the effect of personality traits on individual aggression. Subsequently, mood mediated the impact of happiness on aggressive behaviors across two subgroup splits. Functional imaging data revealed that individuals with higher levels of happiness exhibited reduced amygdala reactivity to fearful faces, as evidenced by a conventional face-matching task (n = 104). Moreover, IS-RSA demonstrated that these participants manifested similar neural activation patterns when processing fearful faces within the visual pathway, but not within the emotional network (e.g., amygdala). Morphological observations (n = 425) indicated that individuals with similar high happiness levels exhibited comparable gray matter volume patterns within several networks, including the default mode network, fronto-parietal network, visual network, and attention network. Collectively, these findings offer early neural evidence supporting the proposition that happy individuals may share common neural characteristics.

Inferring single-cell spatial gene expression with tissue morphology via explainable deep learning.

The spatial arrangement of cells is vital in developmental processes and organogenesis in multicellular life forms. Deep learning models trained with spatial omics data uncover complex patterns and relationships among cells, genes, and proteins in a high-dimensional space, providing new insights into biological processes and diseases. State-of-the-art in silico spatial multi-cell gene expression methods using histological images of tissue stained with hematoxylin and eosin (H&E) to characterize cellular heterogeneity. These computational techniques offer the advantage of analyzing vast amounts of spatial data in a scalable and automated manner, thereby accelerating scientific discovery and enabling more precise medical diagnostics and treatments. In this work, we developed a vision transformer (ViT) framework to map histological signatures to spatial single-cell transcriptomic signatures, named SPiRiT ( S patial Omics P rediction and R eproducibility integrated T ransformer). Our framework was enhanced by integrating cross validation with model interpretation during hyper-parameter tuning. SPiRiT predicts single-cell spatial gene expression using the matched histopathological image tiles of human breast cancer and whole mouse pup, evaluated by Xenium (10x Genomics) datasets. Furthermore, ViT model interpretation reveals the high-resolution, high attention area (HAR) that the ViT model uses to predict the gene expression, including marker genes for invasive cancer cells ( FASN ), stromal cells ( POSTN ), and lymphocytes ( IL7R ). In an apple-to-apple comparison with the ST-Net Convolutional Neural Network algorithm, SPiRiT improved predictive accuracy by 40% using human breast cancer Visium (10x Genomics) dataset. Cancer biomarker gene prediction and expression level are highly consistent with the tumor region annotation. In summary, our work highlights the feasibility to infer spatial single-cell gene expression using tissue morphology in multiple-species, i.e., human and mouse, and multi-organs, i.e., mouse whole body morphology. Importantly, incorporating model interpretation and vision transformer is expected to serve as a general-purpose framework for spatial transcriptomics.

Deep neural network expressivity for optimal stopping problems

This article studies deep neural network expression rates for optimal stopping problems of discrete-time Markov processes on high-dimensional state spaces. A general framework is established in which the value function and continuation value of an optimal stopping problem can be approximated with error at most ε\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$\\varepsilon $\\end{document} by a deep ReLU neural network of size at most κdqε−r\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$\\kappa d^{\\mathfrak{q}} \\varepsilon ^{-\\mathfrak{r}}$\\end{document}. The constants κ,q,r≥0\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$\\kappa ,\\mathfrak{q},\\mathfrak{r} \\geq 0$\\end{document} do not depend on the dimension d\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$d$\\end{document} of the state space or the approximation accuracy ε\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$\\varepsilon $\\end{document}. This proves that deep neural networks do not suffer from the curse of dimensionality when employed to approximate solutions of optimal stopping problems. The framework covers for example exponential Lévy models, discrete diffusion processes and their running minima and maxima. These results mathematically justify the use of deep neural networks for numerically solving optimal stopping problems and pricing American options in high dimensions.

Ab Initio-Based Bond Order Potential for Arsenene Polymorphs Developed via Hierarchical Reinforcement Learning.

Arsenene, a less-explored two-dimensional material, holds the potential for applications in wearable electronics, memory devices, and quantum systems. This study introduces a bond-order potential model with Tersoff formalism, the ML-Tersoff, which leverages multireward hierarchical reinforcement learning (RL), trained on an ab initio data set. This data set covers a spectrum of properties for arsenene polymorphs, enhancing our understanding of its mechanical and thermal behaviors without the complexities of traditional models requiring multiple parameter sets. Our RL strategy utilizes decision trees coupled with a hierarchical reward strategy to accelerate convergence in high-dimensional continuous search spaces. Unlike the Stillinger-Weber approach, which demands separate formalisms for buckled and puckered forms, the ML-Tersoff model concurrently captures multiple properties of the two polymorphs by effectively representing the local environment, thereby avoiding the need for different atomic types. We apply the ML model to understand the mechanical and thermal properties of the arsenene polymorphs and nanostructures. We observe an inverse relationship between the critical strain and temperature in arsenene. Thermal conductivity calculations in nanosheets show good agreement with ab initio data, reflecting a decrease in thermal conductivity attributable to increased anharmonic effects at higher temperatures. We also apply the model to predict the thermal behavior of arsenene nanotubes.

A novel method of nonuniform phase space reconstruction for multivariate prediction of daily runoff

Phase space reconstruction is crucial for predicting chaotic hydrological time series. However, traditional multivariate phase space reconstruction methods, such as high-dimensional and low-dimensional phase space reconstruction (HDPSR and LDPSR) neglect variable interdependence, resulting in redundant information in the reconstructed phase space and affecting the model prediction accuracy. To address this limitation, this study proposes a new nonuniform phase space reconstruction (NUPSR) method that combines the minimum redundancy maximum relevance criterion and conditional entropy. Then, using HDPSR, LDPSR, NUPSR, particle swarm optimization (PSO), support vector regression (SVR), and bidirectional long- and short-term memory neural networks (BiLSTM), the models HDPSR-PSO-SVR, LDPSR-PSO-SVR, NUPSR-PSO-SVR, HDPSR-PSO-BiLSTM, LDPSR-PSO-BiLSTM, and NUPSR-PSO-BiLSTM are built to evaluate the performance of the NUPSR method. To demonstrate the effectiveness of the NUPSR method in multistep daily runoff prediction, the models PSO-NUPSR-BiLSTM, LDPSR-PSO-BiLSTM, and HDPSR-PSO-BiLSTM are also built. The multifactor daily runoff data from five hydrological stations in the Weihe River Basin are used to evaluate the prediction performance of all models. The results show that the state variables obtained by NUPSR are more independent and less redundant than those obtained by HDPSR and LDPSR, as evidenced by the embedded state variables and lower embedding dimension of NUPSR and the performance of the model based on NUPSR outperforms based on HDPSR and LDPSR. Particularly, the PSO-NUPSR-BiLSTM model exhibits a slower decrease in prediction accuracy compared to the other two models as the number of prediction steps increases. In summary, the NUPSR method effectively selects and reconstructs predictors, significantly improves the prediction accuracy of the coupled models, and has broad application prospects in multivariate prediction in fields such as hydrology.

Patient-specific reference model estimation for orthognathic surgical planning.

Accurate estimation of reference bony shape models is fundamental for orthognathic surgical planning. Existing methods to derive this model are of two types: one determines the reference model by estimating the deformation field to correct the patient's deformed jaw, often introducing distortions in the predicted reference model; The other derives the reference model using a linear combination of their landmarks/vertices but overlooks the intricate nonlinear relationship between the subjects, compromising the model's precision and quality. We have created a self-supervised learning framework to estimate the reference model. The core of this framework is a deep query network, which estimates the similarity scores between the patient's midface and those of the normal subjects in a high-dimensional space. Subsequently, it aggregates high-dimensional features of these subjects and projects these features back to 3D structures, ultimately achieving a patient-specific reference model. Our approach was trained using a dataset of 51 normal subjects and tested on 30 patient subjects to estimate their reference models. Performance assessment against the actual post-operative bone revealed a mean Chamfer distance error of 2.25 mm and an average surface distance error of 2.30 mm across the patient subjects. Our proposed method emphasizes the correlation between the patients and the normal subjects in a high-dimensional space, facilitating the generation of the patient-specific reference model. Both qualitative and quantitative results demonstrate its superiority over current state-of-the-art methods in reference model estimation.

A biologically inspired computational model of human ventral temporal cortex

Our minds represent miscellaneous objects in the physical world metaphorically in an abstract and complex high-dimensional object space, which is implemented in a two-dimensional surface of the ventral temporal cortex (VTC) with topologically organized object selectivity. Here we investigated principles guiding the topographical organization of object selectivities in the VTC by constructing a hybrid Self-Organizing Map (SOM) model that harnesses a biologically inspired algorithm of wiring cost minimization and adheres to the constraints of the lateral wiring span of human VTC neurons. In a series of in silico experiments with functional brain neuroimaging and neurophysiological single-unit data from humans and non-human primates, the VTC-SOM predicted the topographical structure of fine-scale category-selective regions (face-, tool-, body-, and place-selective regions) and the boundary in large-scale abstract functional maps (animate vs. inanimate, real-word small-size vs. big-size, central vs. peripheral), with no significant loss in functionality (e.g., categorical selectivity and view-invariant representations). In addition, when the same principle was applied to V1 orientation preferences, a pinwheel-like topology emerged, suggesting the model's broad applicability. In summary, our study illustrates that the simple principle of wiring cost minimization, coupled with the appropriate biological constraint of lateral wiring span, is able to implement the high-dimensional object space in a two-dimensional cortical surface.

Application of support vector machines and genetic algorithms to fluid identification in Offshore Granitic subduction hill reservoirs

YL8 area granite submarine is located in the Songnan low uplift of Qiongdongnan Basin, submarine reservoir fracture development, non-homogeneous strong. Geophysical logging and gas logging do not show a clear pattern of response to the fluid properties of submarine reservoirs, and it is difficult to use logging information to linearly classify granite submarine reservoir fluids in two dimensions. Support Vector Machines (SVM) can map multi-dimensional data into high-dimensional space and construct hyperplanes in high-dimensional space to categorize the samples, which meets the need to incorporate logging curves and mud gas parameters that show complex response relationships with the fluid types of subducted reservoirs into the model.Therefore, in this paper, a support vector machine (GA-SVM) granite subduction reservoir fluid prediction model based on genetic algorithm optimisation is constructed. Firstly, the petrophysical characteristics of different reservoirs in the granite subduction hill were analysed in detail, acquisition and standardisation of logging and mud gas logging multi-dimensional parameters sensitive to reservoir fluids, inputting sensitive parameters into GA-SVM mapping multi-dimensional parameters to higher dimensional space using Gaussian radial kernel functions, using genetic algorithms to perform crossover and mutation operations on the kernel parameter g and the penalty parameter C to obtain the optimal parameter combinations, optimising the number of GA-SVM iterations and model accuracy. The GA-SVM predictions were compared with two other machine learning predictions. As demonstrated through actual case studies in the YL8 area, fluid type recognition compliance rate of 88.2% by GA-SVM, GA-SVM effectively improve the compliance rate of fluid identification in granite subduction reservoirs, provides a new idea for logging interpretation of complex reservoirs in granite subduction reservoirs.

Optimization investigation on variable-density multi-layer insulation coupled with vapor-cooled shield for liquid hydrogen tank based on sequential quadratic programming

The MLI (multi-layer insulation), commonly used in liquid hydrogen tank, acts to reduce HLF (heat leakage flux) into the tank and slow down tank pressurization. It is usually optimally designed into three or four regions, with the same RS spacing in every region, which is regarded as the discontinuous variable density and called VDMLI (variable-density multi-layer insulation). However, the VCS (vapor-cooled shield) and P-O (para-to-ortho hydrogen conversion) in VDMLI are not considered in the optimal design of VDMLI. Therefore, a kind of nonlinear programming algorithm named SQP (sequential quadratic programming), in which HLF solver of liquid hydrogen tank is embedded, is firstly introduced to obtain the optimized distribution of RS (radiative shield) spacing to minimize HLF of liquid hydrogen storage tank. The HLF solver is a numerical model of VDMLI coupled with VCS and P-O, and SQP can be regarded as the optimization process of searching for an optimal solution in high dimensional space, under inequality constraints. The calculation results show that the best SN (serial number) of RS for SVCS (single vapor-cooled shield) setting to minimize HLF, in three cases of before optimization with P-O, after optimization with P-O, and after optimization without P-O is 16, 11, and 14 respectively. With P-O, the minimum HLF after optimization is reduced by 8.45% compared with the minimum HLF before optimization. When SVCS is set at the 4th RS, P-O leads to the most decreasing range of HLF, which is 28.3%, while the optimization process leads to the most decreasing range of 48.1% under condition that SVCS is set at the 2nd RS and P-O is coupled. Under condition of no P-O, after optimization, the minimum HLF occurs when the SN of RS where DVCS (double vapor-cooled shield) is set is (8,21), and the minimum HLF is reduced by 9.0%, compared to that before optimization with DVCS, and is reduced by 50.43% compared to that after optimization with SVCS.

Detection and Type Recognition of SAR Artificial Modulation Targets Based on Multi-Scale Amplitude-Phase Features

With respect to the detection and recognition of an Artificial Modulation Target (AMT) with different modulated types, the state-of-the-art methods generally suffer the deficiencies of overfitting and insufficient generalization of existing neural network solutions. To address these problems, this paper proposes a multi-scale amplitude-phase feature discrimination method for AMTs in SAR images. First, a multi-type modulated AMT Dataset is generated (AMT Detection and Modulation Type Recognition Dataset, ADMTR Dataset), wherein the factors of jamming position, jamming-to-signal ratio (JSR), and the modulated parameter are considered to enhance the generalization. Second, a Multi-Input Multi-Output Fusion Wavelet Neural Network (MIMOFWTNN) is established, which not only uses the amplitude information of the scene but also adequately makes use of the phase and high-frequency information. This empowers us to detect the AMT in a higher dimensional feature space such that the type recognition can be implemented with more certainty. Analysis and discussions conducted on comparison experiments and ablation experiments demonstrate that the proposed network can achieve an average accuracy of 96.96% on the cross-validation set and a correct rate of 99.0% on the completely independent test set, which outperforms the compared methods.

SpaDE: Semantic Locality Preserving Biclustering for Neuroimaging Data.

The most discriminative and revealing patterns in the neuroimaging population are often confined to smaller subdivisions of the samples and features. Especially in neuropsychiatric conditions, symptoms are expressed within micro subgroups of individuals and may only underly a subset of neurological mechanisms. As such, running a whole-population analysis yields suboptimal outcomes leading to reduced specificity and interpretability. Biclustering is a potential solution since subject heterogeneity makes one-dimensional clustering less effective in this realm. Yet, high dimensional sparse input space and semantically incoherent grouping of attributes make post hoc analysis challenging. Therefore, we propose a deep neural network called semantic locality preserving auto decoder (SpaDE), for unsupervised feature learning and biclustering. SpaDE produces coherent subgroups of subjects and neural features preserving semantic locality and enhancing neurobiological interpretability. Also, it regularizes for sparsity to improve representation learning. We employ SpaDE on human brain connectome collected from schizophrenia (SZ) and healthy control (HC) subjects. The model outperforms several state-of-the-art biclustering methods. Our method extracts modular neural communities showing significant (HC/SZ) group differences in distinct brain networks including visual, sensorimotor, and subcortical. Moreover, these bi-clustered connectivity substructures exhibit substantial relations with various cognitive measures such as attention, working memory, and visual learning.

Generative learning facilitated discovery of high-entropy ceramic dielectrics for capacitive energy storage

Dielectric capacitors offer great potential for advanced electronics due to their high power densities, but their energy density still needs to be further improved. High-entropy strategy has emerged as an effective method for improving energy storage performance, however, discovering new high-entropy systems within a high-dimensional composition space is a daunting challenge for traditional trial-and-error experiments. Here, based on phase-field simulations and limited experimental data, we propose a generative learning approach to accelerate the discovery of high-entropy dielectrics in a practically infinite exploration space of over 1011 combinations. By encoding-decoding latent space regularities to facilitate data sampling and forward inference, we employ inverse design to screen out the most promising combinations via a ranking strategy. Through only 5 sets of targeted experiments, we successfully obtain a Bi(Mg0.5Ti0.5)O3-based high-entropy dielectric film with a significantly improved energy density of 156 J cm−3 at an electric field of 5104 kV cm−1, surpassing the pristine film by more than eight-fold. This work introduces an effective and innovative avenue for designing high-entropy dielectrics with drastically reduced experimental cycles, which could be also extended to expedite the design of other multicomponent material systems with desired properties.

A Sampling Strategy for High-Dimensional, Simulation-Based Transportation Optimization Problems

When tackling high-dimensional, continuous simulation-based optimization (SO) problems, it is important to balance exploration and exploitation. Most past SO research focuses on the enhancement of exploitation techniques. The exploration technique of an SO algorithm is often defined as a general-purpose sampling distribution, such as the uniform distribution, which is inefficient at searching high-dimensional spaces. This work is motivated by the formulation of exploration techniques that are suitable for large-scale transportation network problems and high-dimensional optimization problems. We formulate a sampling mechanism that combines inverse cumulative distribution function sampling with problem-specific structural information of the underlying transportation problem. The proposed sampling distribution assigns greater sampling probability to points with better expected performance as defined by an analytical network model. Validation experiments on a toy network illustrate that the proposed sampling distribution has important commonalities with the underlying and typically unknown true sampling distribution of the simulator. We study a high-dimensional traffic signal control case study of Midtown Manhattan in New York City. The results show that the use of the proposed sampling mechanism as part of an SO framework can help to efficiently identify solutions with good performance. Using the analytical information for exploration, regardless of whether it is used for exploitation, outperforms benchmarks that do not use it, including standard Bayesian optimization. Using the analytical information for exploration only yields solutions with similar performance than when the information is used for exploitation only, reducing the total compute times by 65%. This paper sheds light on the importance of developing suitable exploration techniques to enhance both the scalability and the compute efficiency of general-purpose SO algorithms. Funding: T. Tay thanks the Agency for Science, Technology and Research (A*STAR) Singapore for funding his work. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2023.0110 .