Inter-feature Relationships Research Articles

A rotated object detection strategy for remote sensing images using misaligned cross-fusion structures

Remote sensing image object detection is a challenging task with a focus on detection accuracy. In the object detection task of remote sensing images, scenes often contain objects with varying scales and dense arrays, leading to issues such as low accuracy, missed detections, and false alarms. To address these challenges, this paper introduces MCSC-Net, a rotated object detector, designed to enhance detection performance for objects of different scales in densely arranged scenarios. The proposed detector features a novel neck network named MCFN-V3, which incorporated a cross-fusion structure. MCFN-V3 facilitates simultaneous feature extraction in upper and lower layers with feedback to the middle layer. Through the cross-fusion of feature layers, it achieves the integration of multi-scale feature information, thereby enhancing the network's detection capabilities for objects at multiple scales. Additionally, the paper presents the STC module to address the problem of poor feature correlation in high-resolution image processing by CNN networks. This module improves feature expressiveness and range, strengthening inter-feature relationships within layers. Furthermore, in the target positioning stage, the paper transforms the angle regression problem into a classification task, making the network more suitable for detecting rotated objects in dense scenes. To assess the effectiveness of the algorithm, experiments were conducted on two publicly available remote sensing datasets, DOTA and UCAS-AOD. Our method achieved a multiclass average precision (mAP) of 77.4 % on DOTA and an outstanding performance of 97.0 % on UCAS-AOD. These experimental results validate the effectiveness of the proposed approach.

DDANF: Deep denoising autoencoder normalizing flow for unsupervised multivariate time series anomaly detection

In recent years, the proliferation of IoT technologies and the widespread adoption of wireless sensors across various critical infrastructures such as power plants, service monitoring systems, space and earth exploration missions, and water treatment facilities have resulted in the generation of vast quantities of multivariate time series data. Within this context, unsupervised anomaly detection has emerged as a pivotal yet challenging problem in time series research, necessitating machine learning models capable of identifying rare anomalies amidst massive datasets. Traditionally, unsupervised methods have approached this issue by learning representations of primary patterns within sequences and detecting deviations through reconstruction errors. However, the effectiveness of this approach is often limited due to the intricate dynamics and diverse patterns inherent in these dynamic systems. Moreover, many existing unsupervised anomaly detection techniques fail to fully exploit inter-feature relationships within multivariate time series data, thereby overlooking a crucial criterion for accurate detection. To address these shortcomings, this paper introduces a novel unsupervised method for multivariate time series anomaly detection based on normalized flows and autoencoders. Central to our approach is the incorporation of a channel shuffling mechanism during training, enhancing the model’s capacity to discern inter-channel patterns and anomalies. Concurrently, the application of normalized flows within the autoencoder framework serves to constrain the latent space, effectively isolating anomalies and improving detection accuracy. Experimental validation conducted on two large-scale public datasets demonstrates the efficacy of the proposed method compared to established benchmarks, highlighting its superior performance.

Trajectories and revolutions in popular melody based on U.S. charts from 1950 to 2023

In the past century, the history of popular music has been analyzed from many different perspectives, with sociologists, musicologists and philosophers all offering distinct narratives characterizing the evolution of popular music. However, quantitative studies on this subject began only in the last decade and focused on features extracted from raw audio, which limits the scope to low-level components of music. The present study investigates the evolution of a more abstract dimension of popular music, specifically melody, using a new dataset of popular melodies spanning from 1950 to 2023. To identify "melodic revolutions", changepoint detection was applied to a multivariate time series comprising features related to the pitch and rhythmic structure of the melodies. Two major revolutions in 1975 and 2000 and one smaller revolution in 1996, characterized by significant decreases in complexity, were located. The revolutions divided the time series into three eras, which were modeled separately with autoregression, linear regression and vector autoregression. Linear regression of autoregression residuals underscored inter-feature relationships, which become stronger in post-2000 melodies. The overriding pattern emerging from these analyses shows decreasing complexity and increasing note density in popular melodies over time, especially since 2000.

Multi-view representation learning for tabular data integration using inter-feature relationships

Objective:An applied problem facing all areas of data science is harmonizing data sources. Joining data from multiple origins with unmapped and only partially overlapping features is a prerequisite to developing and testing robust, generalizable algorithms, especially in healthcare. This integrating is usually resolved using meta-data such as feature names, which may be unavailable or ambiguous. Our goal is to design methods that create a mapping between structured tabular datasets derived from electronic health records independent of meta-data. Methods:We evaluate methods in the challenging case of numeric features without reliable and distinctive univariate summaries, such as nearly Gaussian and binary features. We assume that a small set of features are a priori mapped between two datasets, which share unknown identical features and possibly many unrelated features. Inter-feature relationships are the main source of identification which we expect. We compare the performance of contrastive learning methods for feature representations, novel partial auto-encoders, mutual-information graph optimizers, and simple statistical baselines on simulated data, public datasets, the MIMIC-III medical-record changeover, and perioperative records from before and after a medical-record system change. Performance was evaluated using both mapping of identical features and reconstruction accuracy of examples in the format of the other dataset. Results:Contrastive learning-based methods overall performed the best, often substantially beating the literature baseline in matching and reconstruction, especially in the more challenging real data experiments. Partial auto-encoder methods showed on-par matching with contrastive methods in all synthetic and some real datasets, along with good reconstruction. However, the statistical method we created performed reasonably well in many cases, with much less dependence on hyperparameter tuning. When validating feature match output in the EHR dataset we found that some mistakes were actually a surrogate or related feature as reviewed by two subject matter experts. Conclusion:In simulation studies and real-world examples, we find that inter-feature relationships are effective at identifying matching or closely related features across tabular datasets when meta-data is not available. Decoder architectures are also reasonably effective at imputing features without an exact match.

Identifying important microbial and genomic biomarkers for differentiating right- versus left-sided colorectal cancer using random forest models

BackgroundColorectal cancer (CRC) is a heterogeneous disease, with subtypes that have different clinical behaviours and subsequent prognoses. There is a growing body of evidence suggesting that right-sided colorectal cancer (RCC) and left-sided colorectal cancer (LCC) also differ in treatment success and patient outcomes. Biomarkers that differentiate between RCC and LCC are not well-established. Here, we apply random forest (RF) machine learning methods to identify genomic or microbial biomarkers that differentiate RCC and LCC.MethodsRNA-seq expression data for 58,677 coding and non-coding human genes and count data for 28,557 human unmapped reads were obtained from 308 patient CRC tumour samples. We created three RF models for datasets of human genes-only, microbes-only, and genes-and-microbes combined. We used a permutation test to identify features of significant importance. Finally, we used differential expression (DE) and paired Wilcoxon-rank sum tests to associate features with a particular side.ResultsRF model accuracy scores were 90%, 70%, and 87% with area under curve (AUC) of 0.9, 0.76, and 0.89 for the human genomic, microbial, and combined feature sets, respectively. 15 features were identified as significant in the model of genes-only, 54 microbes in the model of microbes-only, and 28 genes and 18 microbes in the model with genes-and-microbes combined. PRAC1 expression was the most important feature for differentiating RCC and LCC in the genes-only model, with HOXB13, SPAG16, HOXC4, and RNLS also playing a role. Ruminococcus gnavus and Clostridium acetireducens were the most important in the microbial-only model. MYOM3, HOXC4, Coprococcus eutactus, PRAC1, lncRNA AC012531.25, Ruminococcus gnavus, RNLS, HOXC6, SPAG16 and Fusobacterium nucleatum were most important in the combined model.ConclusionsMany of the identified genes and microbes among all models have previously established associations with CRC. However, the ability of RF models to account for inter-feature relationships within the underlying decision trees may yield a more sensitive and biologically interconnected set of genomic and microbial biomarkers.

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). ARCliDS is composed of two main components: Artifcial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient’s pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Networks (GNN) are applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid nonphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Networks to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. We found that, Double GNN architecture was able to correct the nonphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 [0.03] Gy/frac (mean [sem]) for adaptive RT in NSCLC patients and 2.96 [0.42] Gy/frac for adaptive SBRT HCC compared to the single GNN’s RMSDs of 0.97 [0.12] Gy/frac and 4.75 [0.16] Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. In conclusion, ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.

A New Method for False Alarm Suppression in Heterogeneous Change Detection

Heterogeneous change detection has a wide range of applications in many fields. However, to date, many existing problems of heterogeneous change detection, such as false alarm suppression, have not been specifically addressed. In this article, we discuss the problem of false alarm suppression and propose a new method based on the combination of a convolutional neural network (CNN) and graph convolutional network (GCN). This approach employs a two-channel CNN to learn the feature maps of multitemporal images and then calculates difference maps of different scales, which means that both low-level and high-level features contribute equally to the change detection. The GCN, with a newly built convolution kernel (called the partially absorbing random walk convolution kernel), classifies these difference maps to obtain the inter-feature relationships between true targets and false ones, which can be represented by an adjacent matrix. We use pseudo-label samples to train the whole network, which means our method is unsupervised. Our method is verified on two typical data sets. The experimental results indicate the superiority of our method compared to some state-of-the-art approaches, which proves the efficacy of our method in false alarm suppression.

MedML: Fusing medical knowledge and machine learning models for early pediatric COVID-19 hospitalization and severity prediction

SummaryThe COVID-19 pandemic has caused devastating economic and social disruption. This has led to a nationwide call for models to predict hospitalization and severe illness in patients with COVID-19 to inform the distribution of limited healthcare resources. To address this challenge, we propose a machine learning model, MedML, to conduct the hospitalization and severity prediction for the pediatric population using electronic health records. MedML extracts the most predictive features based on medical knowledge and propensity scores from over 6 million medical concepts and incorporates the inter-feature relationships in medical knowledge graphs via graph neural networks. We evaluate MedML on the National Cohort Collaborative (N3C) dataset. MedML achieves up to a 7% higher AUROC and 14% higher AUPRC compared to the best baseline machine learning models. MedML is a new machine learnig framework to incorporate clinical domain knowledge and is more predictive and explainable than current data-driven methods.

Enabling Fast Exploratory Analyses Over Voluminous Spatiotemporal Data Using Analytical Engines

Fueled by the proliferation of IoT devices and increased adoption of sensing environments the collection of spatiotemporal data has exploded in recent years. Disk based storage systems provide reliable archives but are far too slow for efficient analytics and spatiotemporal datasets quickly exceed the memory capacity of cluster environments. Current solutions focused on in-memory analytics suffer from memory contention and unnecessary network I/O, failing to provide a suitable platform for iterative, exploratory analytics in shared environments. In this work we propose Anamnesis, the first in-memory, sketch aligned, HDFS compliant storage system. Data sketching algorithms reduce dataset sizes by summarizing feature values and inter-feature relationships. Anamnesis leverages data sketches to alleviate memory contention and vastly reduce network I/O during analytics. Upon request, we generate accurate full-resolution datasets with negligible resource and time costs. Datasets are available using a fully HDFS compliant interface allowing Anamnesis to achieve unprecedented compatibility with popular analytics engines. This facilitates adoption into existing workflows by serving as a drop-in replacement for canonical HDFS. We evaluate the system using 2 spatiotemporal datasets, a variety of popular analytics engines, and real-world analytical operations.

Detection of relationships among multi-modal brain imaging meta-features via information flow

BackgroundNeuroscientists and clinical researchers are awash in data from an ever-growing number of imaging and other bio-behavioral modalities. This flow of brain imaging data, taken under resting and various task conditions, combines with available cognitive measures, behavioral information, genetic data plus other potentially salient biomedical and environmental information to create a rich but diffuse data landscape. The conditions being studied with brain imaging data are often extremely complex and it is common for researchers to employ more than one imaging, behavioral or biological data modality (e.g., genetics) in their investigations. While the field has advanced significantly in its approach to multimodal data, the vast majority of studies still ignore joint information among two or more features or modalities. New methodWe propose an intuitive framework based on conditional probabilities for understanding information exchange between features in what we are calling a feature meta-space; that is, a space consisting of many individual featurae spaces. Features can have any dimension and can be drawn from any data source or modality. No a priori assumptions are made about the functional form (e.g., linear, polynomial, exponential) of captured inter-feature relationships. ResultsWe demonstrate the framework’s ability to identify relationships between disparate features of varying dimensionality by applying it to a large multi-site, multi-modal clinical dataset, balance between schizophrenia patients and controls. In our application it exposes both expected (previously observed) relationships, and novel relationships rarely considered investigated by clinical researchers. Comparison with existing method(s)To the best of our knowledge there is not presently a comparably efficient way to capture relationships of indeterminate functional form between features of arbitrary dimension and type. We are introducing this method as an initial foray into a space that remains relatively underpopulated. ConclusionsThe framework we propose is powerful, intuitive and very efficiently provides a high-level overview of a massive data space. In our application it exposes both expected relationships and relationships very rarely considered worth investigating by clinical researchers.

Synopsis: A Distributed Sketch over Voluminous Spatiotemporal Observational Streams

Networked observational devices have proliferated in recent years, contributing to voluminous data streams from a variety of sources and problem domains. These streams often have a spatiotemporal component and include multidimensional features of interest. Processing such data in an offline fashion using batch systems or data warehouses is costly from both a storage and computational standpoint, and in many situations the insights derived from the data streams are useful only if they are timely. In this study, we propose Synopsis , an online, distributed sketch that is constructed from voluminous spatiotemporal data streams. The sketch summarizes feature values and inter-feature relationships in memory to facilitate real-time query evaluations and to serve as input to computations expressed using analytical engines. As the data streams evolve, Synopsis performs targeted dynamic scaling to ensure high accuracy and effective resource utilization. We evaluate our system in the context of two real-world spatiotemporal datasets and demonstrate its efficacy in both scalability and query evaluations.

Associative CAD references in the neutral parametric canonical form

ABSTRACTDue to the multiplicity of computer-aided engineering applications used in industry, interoperability between programs has become increasingly important. A 1999 study by the National Institute for Standards and Technology (NIST) estimated that inadequate interoperability between the original engineering manufacturers (OEM) and their suppliers cost the US automotive industry over $1 billion per year, with the majority spent fixing data after translations. The Neutral Parametric Canonical Form (NPCF) prototype standard developed by the BYU Site of the NSF Center for e-Design offers a solution to this problem by enabling real-time collaboration between heterogeneous systems while preserving design intent. The NPCF is implemented within a SQL database and defines the schema both for neutral features and for the parameters defining the inter-feature relationships and associations.

Locally Discriminative Coclustering

Different from traditional one-sided clustering techniques, coclustering makes use of the duality between samples and features to partition them simultaneously. Most of the existing co-clustering algorithms focus on modeling the relationship between samples and features, whereas the intersample and interfeature relationships are ignored. In this paper, we propose a novel coclustering algorithm named Locally Discriminative Coclustering (LDCC) to explore the relationship between samples and features as well as the intersample and interfeature relationships. Specifically, the sample-feature relationship is modeled by a bipartite graph between samples and features. And we apply local linear regression to discovering the intrinsic discriminative structures of both sample space and feature space. For each local patch in the sample and feature spaces, a local linear function is estimated to predict the labels of the points in this patch. The intersample and interfeature relationships are thus captured by minimizing the fitting errors of all the local linear functions. In this way, LDCC groups strongly associated samples and features together, while respecting the local structures of both sample and feature spaces. Our experimental results on several benchmark data sets have demonstrated the effectiveness of the proposed method.