Search

For two-dimensional (2D) materials, the exact thickness of the material often dictates its physical and chemical properties. The 2D quantum material WTe2 possesses properties that vary significantly from a single layer to multiple layers, yet it has a complicated crystal structure that makes it difficult to differentiate thicknesses in atomic-resolution images. Furthermore, its air sensitivity and susceptibility to electron beam-induced damage heighten the need for direct ways to determine the thickness and atomic structure without acquiring multiple measurements or transferring samples in ambient atmosphere. Here, we demonstrate a new method to identify the thickness up to ten van der Waals layers in Td-WTe2 using atomic-resolution high-angle annular dark-field scanning transmission electron microscopy image simulation. Our approach is based on analyzing the intensity line profiles of overlapping atomic columns and building a standard neural network model from the line profile features. We observe that it is possible to clearly distinguish between even and odd thicknesses (up to seven layers), without using machine learning, by comparing the deconvoluted peak intensity ratios or the area ratios. The standard neural network model trained on the line profile features allows thicknesses to be distinguished up to ten layers and exhibits an accuracy of up to 94% in the presence of Gaussian and Poisson noise. This method efficiently quantifies thicknesses in Td-WTe2, can be extended to related 2D materials, and provides a pathway to characterize precise atomic structures, including local thickness variations and atomic defects, for few-layer 2D materials with overlapping atomic column positions. [ABSTRACT FROM AUTHOR]

The thermophysical properties of liquid metals and alloys are crucial to explore the intrinsic mechanisms of the solidification process, glass formation, and fluid dynamics. The deep learning approaches have emerged as powerful tools in numerous scientific fields and exhibit extraordinary accuracy in the estimation of physical properties and structural characteristics for various materials. In this Tutorial, focusing on the thermophysical properties of liquid multicomponent alloys, deep learning methods, including both supervised learning and active learning, are introduced. Combined with the verification from electrostatic and electromagnetic levitation experiments, the influences of training parameters and methods on the accuracy to obtain interatomic potential by deep learning are revealed on the basis of deep neural network algorithm. As a result, this prediction method of liquid state properties for multicomponent alloys exhibited the dual advantages of high accuracy derived from density functional theory and low computational cost associated with empirical potential. [ABSTRACT FROM AUTHOR]

In recent times, a variety of hybrid quantum–classical algorithms have been developed that aim to calculate the ground state energies of molecular systems on Noisy Intermediate-Scale Quantum (NISQ) devices. Albeit the utilization of shallow depth circuits in these algorithms, the optimization of ansatz parameters necessitates a substantial number of quantum measurements, leading to prolonged runtimes on the scantly available quantum hardware. Through our work, we lay the general foundation for an interdisciplinary approach that can be used to drastically reduce the dependency of these algorithms on quantum infrastructure. We showcase these pertinent concepts within the framework of the recently developed Projective Quantum Eigensolver (PQE) that involves iterative optimization of the nonlinearly coupled parameters through repeated residue measurements on quantum hardware. We demonstrate that one may perceive such a nonlinear optimization problem as a collective dynamic interplay of fast and slow relaxing modes. As such, the synergy among the parameters is exploited using an on-the-fly supervised machine learning protocol that dynamically casts the PQE optimization into a smaller subspace by reducing the effective degrees of freedom. We demonstrate analytically and numerically that our proposed methodology ensures a drastic reduction in the number of quantum measurements necessary for the parameter updates without compromising the characteristic accuracy. Furthermore, the machine learning model may be tuned to capture the noisy data of NISQ devices, and thus the predicted energy is shown to be resilient under a given noise model. [ABSTRACT FROM AUTHOR]

Memristive devices with both electrically and optically induced synaptic dynamic behaviors will be crucial to the accomplishment of brain-inspired neuromorphic computing systems, in which the resistive materials and device architectures are two of the most important cornerstones, but still under challenge. Herein, kuramite Cu3SnS4 is newly introduced into poly-methacrylate as the switching medium to construct memristive devices, and the expected high-performance bio-mimicry of diverse optoelectronic synaptic plasticity is demonstrated. In addition to the excellent basic performances, such as stable bipolar resistive switching with On/Off ratio of ∼486, Set/Reset voltage of ∼−0.88/+0.96 V, and good retention feature of up to 104 s, the new designs of memristors possess not only the multi-level controllable resistive-switching memory property but also the capability of mimicking optoelectronic synaptic plasticity, including electrically and visible/near-infrared light-induced excitatory postsynaptic currents, short-/long-term memory, spike-timing-dependent plasticity, long-term plasticity/depression, short-term plasticity, paired-pulse facilitation, and "learning-forgetting-learning" behavior as well. Predictably, as a new class of switching medium material, such proposed kuramite-based artificial optoelectronic synaptic device has great potential to be applied to construct neuromorphic architectures in simulating human brain functions. [ABSTRACT FROM AUTHOR]

The structural characterization of proteins with a disorder requires a computational approach backed by experiments to model their diverse and dynamic structural ensembles. The selection of conformational ensembles consistent with solution experiments of disordered proteins highly depends on the initial pool of conformers, with currently available tools limited by conformational sampling. We have developed a Generative Recurrent Neural Network (GRNN) that uses supervised learning to bias the probability distributions of torsions to take advantage of experimental data types such as nuclear magnetic resonance J-couplings, nuclear Overhauser effects, and paramagnetic resonance enhancements. We show that updating the generative model parameters according to the reward feedback on the basis of the agreement between experimental data and probabilistic selection of torsions from learned distributions provides an alternative to existing approaches that simply reweight conformers of a static structural pool for disordered proteins. Instead, the biased GRNN, DynamICE, learns to physically change the conformations of the underlying pool of the disordered protein to those that better agree with experiments. [ABSTRACT FROM AUTHOR]

Once realized, autonomous aerial refueling will revolutionize unmanned aviation by removing current range and endurance limitations. Previous attempts at establishing vision-based solutions have come close but rely heavily on near perfect extrinsic camera calibrations that often change midflight. In this paper, we propose dual object detection, a technique that overcomes such requirement by transforming aerial refueling imagery directly into receiver aircraft reference frame probe-to-drogue vectors regardless of camera position and orientation. These vectors are precisely what autonomous agents need to successfully maneuver the tanker and receiver aircraft in synchronous flight during refueling operations. Our method follows a common 4-stage process of capturing an image, finding 2D points in the image, matching those points to 3D object features, and analytically solving for the object pose. However, we extend this pipeline by simultaneously performing these operations across two objects instead of one using machine learning and add a fifth stage that transforms the two pose estimates into a relative vector. Furthermore, we propose a novel supervised learning method using bounding box corrections such that our trained artificial neural networks can accurately predict 2D image points corresponding to known 3D object points. Simulation results show that this method is reliable, accurate (within 3 cm at contact), and fast (45.5 fps). [ABSTRACT FROM AUTHOR]

Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment planning. Thus, it is of great significance to explore automatic segmentation approaches, among which deep learning-based approaches have evolved rapidly and witnessed remarkable progress in multi-organ segmentation. However, obtaining an appropriately sized and fine-grained annotated dataset of multiple organs is extremely hard and expensive. Such scarce annotation limits the development of high-performance multi-organ segmentation models but promotes many annotation-efficient learning paradigms. Among these, studies on transfer learning leveraging external datasets, semi-supervised learning including unannotated datasets and partially-supervised learning integrating partially-labeled datasets have led the dominant way to break such dilemmas in multi-organ segmentation. We first review the fully supervised method, then present a comprehensive and systematic elaboration of the 3 abovementioned learning paradigms in the context of multi-organ segmentation from both technical and methodological perspectives, and finally summarize their challenges and future trends. [ABSTRACT FROM AUTHOR]

In recent years, the focus has shifted towards leveraging physics-based modelling and data-driven analysis to predict drilling incidents and anomalies in real time, with the goal of reducing non-productive periods. However, much of this attention has directed at specific drilling operations like drilling and tripping, leaving other vital processes, such as wellbore conditioning, comparatively overlooked. The primary objective of this study is to employ data-driven techniques for predicting the dynamic state of the wellbore by utilising sensor data, operating parameters, and surface measurements. Accurate predictions are pivotal for automating these processes, promising significant savings in both redundant time and associated costs, ultimately elevating operational efficiency. In this research, the surface drilling parameters such as flowrate, rotation speed, block position, and drill string length are incorporated with the surface measurements such as hookload, pressure, and torque during wellbore conditioning operation to predict further surface sensor measurements. Different parameter settings are evaluated to find the best approach. Six supervised learning algorithms are used to select the best prediction method. The findings reveal that considering all surface parameters and measurements yields the most accurate predictions. Among various single and multi-target regression methods, including deep learning approaches, the Gaussian process and random forest models exhibit the lowest prediction errors. By reliably predicting and understanding wellbore behaviour, this research paves the way for more efficient and autonomous drilling operations in the future, bridging a critical gap in the industry's automation capabilities. [ABSTRACT FROM AUTHOR]

Due to its plug-and-play functionality and wide device support, the universal serial bus (USB) protocol has become one of the most widely used protocols. However, this widespread adoption has introduced a significant security concern: the implicit trust provided to USB devices, which has created a vast array of attack vectors. Malicious USB devices exploit this trust by disguising themselves as benign peripherals and covertly implanting malicious commands into connected host devices. Existing research employs supervised learning models to identify such malicious devices, but our study reveals a weakness in these models when faced with sophisticated data poisoning attacks. We propose, design and implement a sophisticated adversarial data poisoning attack to demonstrate how these models can be manipulated to misclassify an attack device as a benign device. Our method entails generating keystroke data using a microprogrammable keystroke attack device. We develop adversarial attacker by meticulously analyzing the data distribution of data features generated via USB keyboards from benign users. The initial training data is modified by exploiting firmware-level modifications within the attack device. Upon evaluating the models, our findings reveal a significant decrease from 99 to 53% in detection accuracy when an adversarial attacker is employed. This work highlights the critical need to reevaluate the dependability of machine learning-based USB threat detection mechanisms in the face of increasingly sophisticated attack methods. The vulnerabilities demonstrated highlight the importance of developing more robust and resilient detection strategies to protect against the evolution of malicious USB devices. [ABSTRACT FROM AUTHOR]

An intrusion detection system (IDS) is a system that monitors network traffic for malicious activity and generates alerts. In anomaly-based detection, machine learning (ML) algorithms exploit various statistical and probabilistic methods to learn from past or historical experience and detect valuable patterns from large, unstructured, and complex datasets. ML-based network intrusion detection aims to identify malicious behavior and alert a system administrator when an intruder tries to penetrate the network. This paper deals with the study, strategic construction, and implementation of a network intrusion detection model based on ML methods. Among the available IDS datasets, five of the most relevant are chosen for the experimental analysis, which are NSL-KDD-2009, CIC-IDS2017, CIC-IDS2018, IoTID20, and UNSW-NB15 datasets. In order to reduce the computation time in the training sample and achieve computational complexity O (N 2.38 ± δ) , we propose a computationally efficient and feasible algorithmic framework for analyzing the network traffic data. The developed approach mainly consists of two phases, i.e., "Scatter Matrices and Eigenvalue Computation based feature Selection" and "Classification procedure for the reduced dimension data." Experimental evaluation of various test case scenarios for the chosen datasets is carried out in the simulation setting. It is observed that the test results outperform the existing intrusion detection methods for detecting certain attack categories. [ABSTRACT FROM AUTHOR]

Picking stack velocity from seismic velocity spectra is a fundamental method in seismic stack velocity analysis. With the increase in the scale of seismic data acquisition, manual picking cannot achieve the required efficiency. Therefore, an automatic picking algorithm is urgently needed now. Despite some supervised deep learning–based picking approaches that have been proposed, they heavily rely on sufficient training samples and lack interpretability. In contrast, utilizing physical knowledge to develop semi‐data‐driven methods has the potential to efficiently solve this problem. Thus, we propose a semi‐supervised ensemble learning method to reduce the reliance on manually labelled data and improve interpretability by incorporating the interval velocity constraint. Semi‐supervised ensemble learning fuses the information of the estimated spectrum, nearby velocity spectra and few‐shot manual picking to recognize the velocity picking. Test results of both the synthetic and field datasets indicate that semi‐supervised ensemble learning achieves more reliable and precise picking than traditional clustering‐based techniques and the currently popular convolutional neural network method. [ABSTRACT FROM AUTHOR]

Seismic inversion is an important tool for reservoir characterization. The inversion results are significantly impacted by a reliable initial model. Conventional well interpolation methods are not able to meet the needs of seismic inversion for lateral heterogeneous reservoirs. Inspired by the sequence modelling network and seismic inversion in the Laplace–Fourier domain, we propose an initial model‐building method using semi‐supervised learning strategy. The proposed method considers spatial information to ensure the horizontal continuity of the initial model. Based on the fact that the low‐frequency components of seismic signals in the Laplace–Fourier domain are easier to obtain, we use the forward model in the Laplace–Fourier domain to replace the time‐domain forward model. The proposed workflow was validated using the Marmousi II model. Although the training was carried out on a small number of low‐frequency impedance traces, the proposed workflow was able to build low‐frequency model for the entire Marmousi II model with a correlation of 98%. Field data examples demonstrate the feasibility and effectiveness of the proposed method. For lateral heterogeneous reservoirs, the proposed method performs better than the well interpolation method. By utilizing the model obtained by the proposed method as the initial low‐frequency model of the conventional inversion method, it is possible to estimate better inversion results. The results of different combinations of training sets demonstrate the stability of the proposed method. This method may still be a viable choice if there is lateral heterogeneity underground but not much well‐logging label data. [ABSTRACT FROM AUTHOR]

This article proposes a framework for the damage assessment of and effect of temperature variations in laminated composites using Lamb waves and unsupervised autonomous features. A network of piezoelectric transducers is employed to generate data for 18 health states of a laminated composite plate. The data is processed with sparse autoencoder (SAE) for unsupervised autonomous features. The discriminative capabilities of the extracted features are confirmed by processing the feature space in the supervised and unsupervised frameworks of machine learning. The confusion matrices of supervised learning provided physical insights into the problem. The feature space was also visualized in two dimensions in an unsupervised manner through principal component analysis (PCA), which revealed physically consistent results for the effect of temperature variations, damage of different severity levels, and the undamaged paths between the actuator and sensors. The healthy state data and information on the paths between the actuator and sensors was processed via SAE for damage localization. The proposed approach can be employed for the autonomous assessment of composite structures for the presence of damage and variations of operating temperatures while using both supervised and unsupervised machine learning algorithms. [ABSTRACT FROM AUTHOR]

Smallholders of dryland ecosystems continue to live below the poverty line while facing significant economic and social deprivation with decreasing landholding. Most dryland farmers perform conventional disintegrated farming practices due to a lack of knowledge and resource inefficiency. This study investigates the possibility of an Integrated Farming System (IFS) to address the current dryland farming issues and explore various factors affecting its adoption among the farming community. This study aims to apply and compare supervised learning techniques to assess the primary drivers affecting the adoption of the IFS in rural southern India. The study shows that organic fertilizer production, farmers' age, and involvement in the extension activity are the major factors affecting the adoption of IFS among dryland farmers. The study supports that small and marginal farmers have a high possibility of realizing the higher benefit from IFS. The study recommends that these components be given proper policy consideration in designing and implementing an effective farming system in dryland areas to improve farmers' income levels. [ABSTRACT FROM AUTHOR]

Recent failures of bridges worldwide highlight the need for robust structural health surveillance systems to provide alerts for early damage and prevent severe loss. Structural health monitoring (SHM) continues to evolve and gain wide adoption among asset managers to mitigate catastrophic failure risks of structural systems. With the prolific integration of SHM with artificial intelligence and internet of things systems becoming prevalent, several data-driven approaches have gained popularity in SHM. However, it is challenging to obtain ground-truth-labelled damage samples for supervised machine learning methods. A class of shallow machine learning methods known as unsupervised methods (e.g. the one-class support vector machine (OCSVM)), which only uses unlabelled data from a healthy state, has been shown to achieve promising results. However, shallow machine learning methods require laborious expert-crafted feature inputs for optimal performance. Inspired by the automatic feature-extraction ability of deep neural networks, unsupervised methods (deep learning models trained without supervisory ground truth labels) such as autoencoder (AE)-based methods were explored to detect structural damage. Results obtained on both real-world data from Sydney Harbour Bridge, one of Australia's iconic structures, and data collected from laboratory specimens demonstrate the effectiveness of the AE-based method over conventional shallow methods such as the OCSVM. [ABSTRACT FROM AUTHOR]

In supervised learning, feature selection methods identify the most relevant predictors to include in a model. For linear models, the inclusion or exclusion of each variable may be represented as a vector of bits playing the role of the genetic material that defines the model. Genetic algorithms reproduce the strategies of natural selection on a population of models to identify the best. We derive the distribution of the importance scores for parallel genetic algorithms under the null hypothesis that none of the features has predictive power. They, hence, provide an objective threshold for feature selection that does not require the visual inspection of a bubble plot. We also introduce the eradication strategy, akin to forward stepwise selection, where the genes of useful variables are sequentially forced into the models. The method is illustrated on real data, and simulation studies are run to describe its performance. [ABSTRACT FROM AUTHOR]

Although current semantic segmentation approaches have achieved impressive performance, their ability to incrementally learn new classes is limited. Moreover, pixel-by-pixel annotations are costly and time-consuming. Therefore, a new field called Weakly-supervised Incremental Learning for Semantic Segmentation (WILSS) has emerged, which learns new classes using image-level labels. However, image-level labels do not provide sufficient detail, and we discover that the state-of-the-art of WILSS suffers from confusion between old knowledge and new knowledge. To address this issue, we propose W eakly-supervised I ncremental learning for S emantic segmentation with Class H ierarchy (WISH), a method that considers the hierarchical structure of each class when determining which knowledge to trust in cases of confusion between old and new knowledge. Our method has achieved new state-of-the-art performances in all settings compared to the previous methods on the Pascal VOC and MS COCO datasets. • Our paper introduces WISH, utilizing hierarchy and image labels for class incremental learning in semantic segmentation. • We efficiently utilize hierarchy, boosting segmentation performances without added costs. • Our method outperforms existing methods in all configurations, showcasing hierarchical integration's effectiveness. [ABSTRACT FROM AUTHOR]

Semi-supervised learning has achieved extraordinary success in prevalent image-classification benchmarks. However, a class-balanced distribution that differs notably from real-world data distribution is required. In general, models trained under class-imbalanced semi-supervised learning conditions are severely biased towards the majority classes. To address this issue, we propose a novel framework called ABAE by implanting an Auxiliary Balanced AutoEncoder branch into existing semi-supervised learning algorithms. Considering that adaptive feature augmentation for different classes can alleviate confirmation bias, we devise a class-aware reconstruction loss to train the AutoEncoder module. To further smooth the output, we adopt a graph-based label propagation scheme at the end of the AutoEncoder. Extensive experiments on CIFAR-10/100-LT, SVHN-LT and Small ImageNet-127 demonstrate the effectiveness of ABAE. • Propose an Auxiliary Balanced AutoEncoder branch(ABAE) with a class-aware reconstruction loss for CISSL. • Utilize the adaptive feature augmentation for different classes to alleviate the confirmation bias. • Adopt a graph-based label propagation scheme to smooth the output of the ABAE. • Demonstrate the effectiveness of the ABAE through experiments on various imbalanced datasets. [ABSTRACT FROM AUTHOR]

Graph semi-supervised learning (GSSL) plays an important role in semi-supervised classification by leveraging the similarity of graph topology and convex optimization with Laplacian-based regularization. Current approaches mainly focus on data representation in the Euclidean space and solely rely on a single graph structure, ignoring the underlined manifold-valued structure of the data. To this end, we propose a novel manifold-based multi-graph embedding (M2GE), which explicitly learns representations on both Riemannian manifold and Euclidean space in the embedding learning process. Incorporating multi-graph structure, the rich and varied features are used by M2GE to more fully capture categorical information, where the heterogeneous spatial representations from manifold are complementary. Extensive experimental results on three popular benchmarks verify demonstrate the superiority of our method over state-of-the art competitors. • A novel manifold-based multi-graph embedding (M2GE) is proposed for semi-supervised classification. • Multi-sampling augmentation is employed to improve the generalization of the model. • M2GE effectively improves the accuracy rate of the semi-supervised classification. [ABSTRACT FROM AUTHOR]

Hyperspectral anomaly detection can separate sparse anomalies from the low-rank background component under an unsupervised behavior due to sufficient spectral information. Therefore, hyperspectral image anomaly detection technology has great application potential and value in public security and national defense. Currently, most existing models attempt to detect anomalous targets with a sparsity prior, without further considering the visual saliency of the targets themselves. To tackle this issue, this paper proposes a saliency-guided sparse low-rank tensor approximation model, called SSLR, to detect anomalous targets from hyperspectral remote sensing images in an unsupervised manner. Specifically, we first explore the saliency information of each pixel for regularizing the sparse anomaly matrix. We then suggest a three-directional tensor nuclear norm to obtain a low-rank background to characterize the background component. We solve the SSLR optimization problem by an efficient alternating direction method of multipliers framework. Experiments conducted on benchmark hyperspectral datasets demonstrate that the proposed SSLR outperforms some state-of-the-art anomaly detection methods. [ABSTRACT FROM AUTHOR]

Objectives: To identify and internally validate metabolites predictive of spontaneous preterm birth (sPTB) using multiple machine learning methods and sequential maternal serum samples, and to predict spontaneous early term birth (sETB) using these metabolites. Design: Case–cohort design within a prospective cohort study. Setting: Cambridge, UK. Population or sample: A total of 399 Pregnancy Outcome Prediction study participants, including 98 cases of sPTB. Methods: An untargeted metabolomic analysis of maternal serum samples at 12, 20, 28 and 36 weeks of gestation was performed. We applied six supervised machine learning methods and a weighted Cox model to measurements at 28 weeks of gestation and sPTB, followed by feature selection. We used logistic regression with elastic net penalty, followed by best subset selection, to reduce the number of predictive metabolites further. We applied coefficients from the chosen models to measurements from different gestational ages to predict sPTB and sETB. Main outcome measures: sPTB and sETB. Results: We identified 47 metabolites, mostly lipids, as important predictors of sPTB by two or more methods and 22 were identified by three or more methods. The best 4‐predictor model had an optimism‐corrected area under the receiver operating characteristics curve (AUC) of 0.703 at 28 weeks of gestation. The model also predicted sPTB in 12‐week samples (0.606, 95% CI 0.544–0.667) and 20‐week samples (0.657, 95% CI 0.597–0.717) and it predicted sETB in 36‐week samples (0.727, 95% CI 0.606–0.849). A lysolipid, 1‐palmitoleoyl‐GPE (16:1)*, was the strongest predictor of sPTB at 12 weeks of gestation (0.609, 95% CI 0.548–0.670), 20 weeks (0.630, 95% CI 0.569–0.690) and 28 weeks (0.660, 95% CI 0.599–0.722), and of sETB at 36 weeks (0.739, 95% CI 0.618–0.860). Conclusions: We identified and internally validated maternal serum metabolites predictive of sPTB. A lysolipid, 1‐palmitoleoyl‐GPE (16:1)*, is a novel predictor of sPTB and sETB. Further validation in external populations is required. [ABSTRACT FROM AUTHOR]

When analyzing screening chest X-ray (CXR) images, radiologists can naturally consider information about the relationships between pathologies, namely pathological co-occurrence, and interdependence. Such topologically meaningful pathological relationships provide complementary a priori knowledge and can improve the radiologist’s classification accuracy. Unfortunately, most existing deep learning systems focus only on regression from input to binary labels, lack the ability to jointly analyze and integrate global and local information from these multiple labels, and the ability to exploit this valuable prior knowledge of topology. We suppose that the algorithm will distinguish co-occurring pathologies easily if it is guided to learn potentially valuable information between multiple pathologies. We propose a novel multi-label global–local analysis method named CXR × MLAGCPL for disease recognition in CXR images. We first designed two methods for constructing graphs: building adaptive local graph on a single image and creating global co-occurrence graph in a data-driven manner. Then two modules, local awareness module (LAM) and global co-occurrence priori learning module (GCPL), were designed to jointly learn local class correlation and global inter-class dependency patterns. We have evaluated the effectiveness of the proposed CXR × MLAGCPL in two large-scale CXR datasets (ChestX-Ray14 and CheXpert). Our model achieved state-of-the-art performance: the mean AUC scores for the 14 pathologies were 0.828 and 0.813, respectively. The proposed LAM and GCPL can jointly effectively improve the recognition performance. Our model is accurate in terms of classification accuracy and generalization due to competing approaches. [ABSTRACT FROM AUTHOR]

Most supervised learning methods require observation data and ground truth pairs as data sets to train the network. However, it is difficult and time-consuming to obtain a large number of high quality data sets, because ground truth is not available in some practical settings, such as medical imaging, dynamic scenes. Deep image prior (DIP) only uses one degraded image for image recovery tasks, which gets rid of the limitation of constructing a large number of training sets but requires an early stop mechanism. In order to further improve the image restoration ability of the DIP model, we combine it with the transformed total variation (TTV) regularization, which is a generalization of the classical total variation (TV) regularization and can achieve better performance for image restoration problems. The proposed method not only uses the deep neural network to capture image prior, but also exploits inherent sparse prior in image gradient domain. In addition, we provide an adaptive weight selection strategy for TTV regularization. The ADMM scheme is employed to solve the proposed models. Numerical results of image restoration illustrate that the proposed methods perform better than the compared methods. • A Transformed Total Variation and Deep Image prior algorithm is proposed for solving the image restoration task. • An adaptive weight selection strategy for TTV regularization is provided. • Numerical results of image restoration illustrate the efficiency of the proposed method among some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Obsessive-compulsive disorder (OCD) is a highly heterogeneous mental condition with a diverse symptom. Existing studies classified OCD on the basis of conventional phenomenology-based taxonomy ignoring the fact that the same subtype identified in accordance with clinical symptom may have different mechanisms and treatment responses. This research involved 50 medicine-free patients with OCD and 50 matched healthy controls (HCs). All the participants were subjected to structural and functional magnetic resonance imaging (MRI). Voxel-based morphometry (VBM) and amplitude of low frequency fluctuation (ALFF) were used to evaluate gray matter volume (GMV) and spontaneous neuronal activities at rest respectively. Similarity network fusion (SNF) was utilized to integrate GMVs and spontaneous neuronal activities, and heterogeneity by discriminant analysis was applied to characterise OCD subtypes. Two OCD subtypes were identified: Subtype 1 exhibited decreased GMVs (i.e., left inferior temporal gyrus, right supplementary motor area and right lingual gyrus) and increased ALFF value (i.e., right orbitofrontal cortex), whereas subtype 2 exhibited increased GMVs (i.e., left cuneus, right precentral gyrus, left postcentral gyrus and left hippocampus) and decreased ALFF value (i.e., right caudate nucleus). Furthermore, the altered GMVs was negatively correlated with abnormal ALFF values in both subtype 1 and 2. This study requires further validation via a larger, independent dataset and should consider the potential influences of psychotropic medication on OCD patients' brain activities. Results revealed two reproducible subtypes of OCD based on underlying multimodal neuroimaging and provided new perspectives on the classification of OCD. • Data-driven subtype analysis of OCD patients rather than previous symptom-based analysis • The multimodal fusion method fuses the magnetic resonance images of two modalities. • Semi-supervised machine learning approach for subtype analysis of obsessive-compulsive disorder [ABSTRACT FROM AUTHOR]

With the rapid development of sensor and communication technology, multi-sensor data is available to monitor the degradation of complex systems and predict the failure modes. However, two huge challenges remain to be resolved: (i) how to predict the failure modes with limited failure mode labeled systems to alleviate the heavy dependence on expert experience; (ii) how to effectively fuze the useful information from the multi-sensor data to achieve an accurate estimation of the degradation status automatically. To address these issues, we propose a novel semi-supervised prognostic model for the systems with partially observable failure modes, where only a small fraction of the systems in the training set are known for their failure modes. First, we develop a graph-based semi-supervised learning method to extract features characterizing the failure modes. Then, we input these features as well as the multi-sensor streams into an elastic net functional regression model to predict the residual useful lifetime. The proposed model is validated by extensive simulation studies and a case study of aircraft turbofan engines available from the NASA repository. [ABSTRACT FROM AUTHOR]

The classification of hyperspectral images (HSI) into categories that correlate to various land cover sorts such as water bodies, agriculture and urban areas, has gained significant attention in research due to its wide range of applications in fields, such as remote sensing, computer vision, and more. Supervised deep learning networks have demonstrated exceptional performance in HSI classification, capitalizing on their capacity for end-to-end optimization and leveraging their strong potential for nonlinear modeling. However, labelling HSIs, on the other hand, necessitates extensive domain knowledge and is a time-consuming and labour-intensive exercise. To address this issue, the proposed work introduces a novel semi-supervised network constructed with an autoencoder, Siamese action, and attention layers that achieves excellent classification accuracy with labelled limited samples. The proposed convolutional autoencoder is trained using the mass amount of unlabelled data to learn the refinement representation referred to as 3D-CAE. The added Siamese network improves the feature separability between different categories and attention layers improve classification by focusing on discriminative information and neglecting the unimportant bands. The efficacy of the proposed model's performance was assessed by training and testing on both same-domain as well as cross-domain data and found to achieve 91.3 and 93.6 for Indian Pines and Salinas, respectively. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is an incurable neurological disorder that degenerates the cerebrospinal nervous system and hinders motor functions. Electroencephalography (EEG) signal analysis can provide reliable information regarding PD conditions. However, EEG is a complex, multichannel, and nonlinear signal with noise that problematizes identifying PD symptoms. A few studies have employed fractal dimension (FD) to extract distinguishing PD features from EEG signals. However, no exploratory study exists, as per our knowledge, on the efficiency of the different FD measures. We aim to conduct a comparative analysis of the various FDs that, as feature extraction measures, can discriminate PD patients who are ON and OFF medication from healthy controls using ML architecture. This study has implemented and analyzed several techniques for segmentation, feature extraction, and ML models. The results show that k-nearest neighbors (KNN) classifier with Higuchi FD and 90% overlap for segmented window delivers the highest accuracies, yielding a mean accuracy of 99.65 ± 0.15 % for PD patients ON medication and 99.45 ± 0.18 % for PD patients OFF medication, respectively. The model accurately identifies the signs of the disease in resting-state EEG with almost equivalent accuracy in both OFF and ON medication patients. To enhance the interpretability in our study, we leveraged XGB's feature importance to generate brain topographic plots. This integration of explainable AI (XAI) enhanced the transparency and comprehensibility of our model's classifications. Additionally, a comparison between the performance of FD and a few entropy measures has also been drawn to validate the significance of FD as a superior feature extraction measure. This study contributes to the body of knowledge with an architectural pipeline for detecting PD in resting-state EEG while emphasizing fractal dimension as an effective way of extracting salient features from EEG signals. [ABSTRACT FROM AUTHOR]

Image detection deep learning models are being used in various fields such as autonomous vehicles, medical, and agriculture. In the defense field, various efforts are being made to apply deep learning models to surveillance systems. Since the defense field deals with important issues such as combat, the reliability of the model is important. Therefore, this study intends to propose a new "strong supervised learning method" to ensure explainability of the defense image classification model. The proposed method is using the knowledge of military experts and the HITL (Human In The Loop) method in which humans and AI interact. This is the learning that provides the data of important parts of objects in addition to the general supervised learning which provides input data and labeling data. The learning process for the additionally provided data is carried out through a loss function of SSIM (Structural Similarity Index Map), which measures the similarity between data of important parts and a feature map of a convolutional neural network. In order to evaluate the proposed methodology, the model learned by general supervised learning and the model learned by the proposed method were compared. The comparison criteria were as follows: first, evaluation of similarity between the results of Grad CAM, a Visual Explain method, along with the data the important parts designated by experts; and second, the classification accuracy of objects. As a result of the experiment using the VGG16, ResNet50, InceptionV3, and Xception models, the similarity between the data of the Grad CAM and the region of interest was improved by an average of 15.52% based on the entire image area. In addition, the classification accuracy showed an average improvement of 4.72% based on Test Set. [ABSTRACT FROM AUTHOR]

Background: Supervised machine learning models have been widely used to predict and get insight into diseases by classifying patients based on personal health records. However, a class imbalance is an obstacle that disrupts the training of the models. In this study, we aimed to address class imbalance with a conditional normalizing flow model, one of the deep-learning-based semi-supervised models for anomaly detection. It is the first introduction of the normalizing flow algorithm for tabular biomedical data. Methods: We collected personal health records from South Korean citizens (n = 706), featuring genetic data obtained from direct-to-customer service (microarray chip), medical health check-ups, and lifestyle log data. Based on the health check-up data, six chronic diseases were labeled (obesity, diabetes, hypertriglyceridemia, dyslipidemia, liver dysfunction, and hypertension). After preprocessing, supervised classification models and semi-supervised anomaly detection models, including conditional normalizing flow, were evaluated for the classification of diabetes, which had extreme target imbalance (about 2%), based on AUROC and AUPRC. In addition, we evaluated their performance under the assumption of insufficient collection for patients with other chronic diseases by undersampling disease-affected samples. Results: While LightGBM (the best-performing model among supervised classification models) showed AUPRC 0.16 and AUROC 0.82, conditional normalizing flow achieved AUPRC 0.34 and AUROC 0.83 during fifty evaluations of the classification of diabetes, whose base rate was very low, at 0.02. Moreover, conditional normalizing flow performed better than the supervised model under a few disease-affected data numbers for the other five chronic diseases – obesity, hypertriglyceridemia, dyslipidemia, liver dysfunction, and hypertension. For example, while LightGBM performed AUPRC 0.20 and AUROC 0.75, conditional normalizing flow showed AUPRC 0.30 and AUROC 0.74 when predicting obesity, while undersampling disease-affected samples (positive undersampling) lowered the base rate to 0.02. Conclusions: Our research suggests the utility of conditional normalizing flow, particularly when the available cases are limited, for predicting chronic diseases using personal health records. This approach offers an effective solution to deal with sparse data and extreme class imbalances commonly encountered in the biomedical context. [ABSTRACT FROM AUTHOR]

Background: The use of amyloid-PET in dementia workup is upcoming. At the same time, amyloid-PET is costly and limitedly available. While the appropriate use criteria (AUC) aim for optimal use of amyloid-PET, their limited sensitivity hinders the translation to clinical practice. Therefore, there is a need for tools that guide selection of patients for whom amyloid-PET has the most clinical utility. We aimed to develop a computerized decision support approach to select patients for amyloid-PET. Methods: We included 286 subjects (135 controls, 108 Alzheimer's disease dementia, 33 frontotemporal lobe dementia, and 10 vascular dementia) from the Amsterdam Dementia Cohort, with available neuropsychology, APOE, MRI and [18F]florbetaben amyloid-PET. In our computerized decision support approach, using supervised machine learning based on the DSI classifier, we first classified the subjects using only neuropsychology, APOE, and quantified MRI. Then, for subjects with uncertain classification (probability of correct class (PCC) < 0.75) we enriched classification by adding (hypothetical) amyloid positive (AD-like) and negative (normal) PET visual read results and assessed whether the diagnosis became more certain in at least one scenario (PPC≥0.75). If this was the case, the actual visual read result was used in the final classification. We compared the proportion of PET scans and patients diagnosed with sufficient certainty in the computerized approach with three scenarios: 1) without amyloid-PET, 2) amyloid-PET according to the AUC, and 3) amyloid-PET for all patients. Results: The computerized approach advised PET in n = 60(21%) patients, leading to a diagnosis with sufficient certainty in n = 188(66%) patients. This approach was more efficient than the other three scenarios: 1) without amyloid-PET, diagnostic classification was obtained in n = 155(54%), 2) applying the AUC resulted in amyloid-PET in n = 113(40%) and diagnostic classification in n = 156(55%), and 3) performing amyloid-PET in all resulted in diagnostic classification in n = 154(54%). Conclusion: Our computerized data-driven approach selected 21% of memory clinic patients for amyloid-PET, without compromising diagnostic performance. Our work contributes to a cost-effective implementation and could support clinicians in making a balanced decision in ordering additional amyloid PET during the dementia workup. [ABSTRACT FROM AUTHOR]

This document discusses the intersection of artificial intelligence (AI) and deep learning with sensor technologies. It highlights the applications of AI and deep learning in various fields such as healthcare, manufacturing, agriculture, transportation, and environmental monitoring. The document also provides a summary of twelve research articles and reviews that explore the integration of AI and deep learning with sensor data for different purposes, including lung cancer screening, reinforcement learning, point cloud sampling, anomaly detection, human activity recognition, semantic segmentation, face recognition, audio super-resolution, industrial control systems, traffic flow prediction, weed detection, and medical diagnostics. These contributions demonstrate the potential of AI and deep learning in optimizing sensor data utilization and solving complex real-world problems. [Extracted from the article]

The field of computer vision has been focusing on achieving accurate three-dimensional (3D) object representations from a single two-dimensional (2D) image through deep artificial neural networks. Recent advancements in 3D shape reconstruction techniques that combine structured light and deep learning show promise in acquiring high-quality geometric information about object surfaces. This paper introduces a new single-shot 3D shape reconstruction method that uses a nonlinear fringe transformation approach through both supervised and unsupervised learning networks. In this method, a deep learning network learns to convert a grayscale fringe input into multiple phase-shifted fringe outputs with different frequencies, which act as an intermediate result for the subsequent 3D reconstruction process using the structured-light fringe projection profilometry technique. Experiments have been conducted to validate the practicality and robustness of the proposed technique. The experimental results demonstrate that the unsupervised learning approach using a deep convolutional generative adversarial network (DCGAN) is superior to the supervised learning approach using UNet in image-to-image generation. The proposed technique's ability to accurately reconstruct 3D shapes of objects using only a single fringe image opens up vast opportunities for its application across diverse real-world scenarios. [ABSTRACT FROM AUTHOR]

This study focuses on advancing the field of remote sensing image target detection, addressing challenges such as small target detection, complex background handling, and dense target distribution. We propose solutions based on enhancing the YOLOv7 algorithm. Firstly, we improve the multi-scale feature enhancement (MFE) method of YOLOv7, enhancing its adaptability and precision in detecting small targets and complex backgrounds. Secondly, we design a modified YOLOv7 global information DP-MLP module to effectively capture and integrate global information, thereby improving target detection accuracy and robustness, especially in handling large-scale variations and complex scenes. Lastly, we explore a semi-supervised learning model (SSLM) target detection algorithm incorporating unlabeled data, leveraging information from unlabeled data to enhance the model's generalization ability and performance. Experimental results demonstrate that despite the outstanding performance of YOLOv7, the mean average precision (MAP) can still be improved by 1.9%. Specifically, under testing on the TGRS-HRRSD-Dataset, the MFE and DP-MLP models achieve MAP values of 93.4% and 93.1%, respectively. Across the NWPU VHR-10 dataset, the three models achieve MAP values of 93.1%, 92.1%, and 92.2%, respectively. Significant improvements are observed across various metrics compared to the original model. This study enhances the adaptability, accuracy, and generalization of remote sensing image object detection. [ABSTRACT FROM AUTHOR]

Stress recognition, particularly using machine learning (ML) with physiological data such as heart rate variability (HRV), holds promise for mental health interventions. However, limited datasets in affective computing and healthcare research can lead to inaccurate conclusions regarding the ML model performance. This study employed supervised learning algorithms to classify stress and relaxation states using HRV measures. To account for limitations associated with small datasets, robust strategies were implemented based on methodological recommendations for ML with a limited dataset, including data segmentation, feature selection, and model evaluation. Our findings highlight that the random forest model achieved the best performance in distinguishing stress from non-stress states. Notably, it showed higher performance in identifying stress from relaxation (F1-score: 86.3%) compared to neutral states (F1-score: 65.8%). Additionally, the model demonstrated generalizability when tested on independent secondary datasets, showcasing its ability to distinguish between stress and relaxation states. While our performance metrics might be lower than some previous studies, this likely reflects our focus on robust methodologies to enhance the generalizability and interpretability of ML models, which are crucial for real-world applications with limited datasets. [ABSTRACT FROM AUTHOR]

Despite recent notable advancements in highlight image restoration techniques, the dearth of annotated data and the lightweight deployment of highlight removal networks pose significant impediments to further advancements in the field. In this paper, to the best of our knowledge, we first propose a semi-supervised learning paradigm for highlight removal, merging the fusion version of a teacher–student model and a generative adversarial network, featuring a lightweight network architecture. Initially, we establish a dependable repository to house optimal predictions as pseudo ground truth through empirical analyses guided by the most reliable No-Reference Image Quality Assessment (NR-IQA) method. This method serves to assess rigorously the quality of model predictions. Subsequently, addressing concerns regarding confirmation bias, we integrate contrastive regularization into the framework to curtail the risk of overfitting on inaccurate labels. Finally, we introduce a comprehensive feature aggregation module and an extensive attention mechanism within the generative network, considering a balance between network performance and computational efficiency. Our experimental evaluations encompass comprehensive assessments on both full-reference and non-reference highlight benchmarks. The results demonstrate conclusively the substantive quantitative and qualitative enhancements achieved by our proposed algorithm in comparison to state-of-the-art methodologies. [ABSTRACT FROM AUTHOR]

Electricity consumption in homes is on the rise due to the increasing prevalence of home appliances and longer hours spent indoors. Home energy management systems (HEMSs) are emerging as a solution to reduce electricity consumption and efficiently manage power usage at home. In the past, numerous studies have been conducted on the management of electricity production and consumption through solar power. However, there are limited human-centered studies focusing on the user's lifestyle. In this study, we propose an Intelligent Home Energy Management System (i-HEMS) and evaluate its energy-saving effectiveness through a demonstration in a standard house in Korea. The system utilizes an IoT environment, PID sensing, and behavioral pattern algorithms. We developed algorithms based on power usage monitoring data of home appliances and human body detection. These algorithms are used as the primary scheduling algorithm and a secondary algorithm for backup purposes. We explored the deep connection between power usage, environmental sensor data, and input schedule data based on Long Short-Term Memory network (LSTM) and developed an occupancy prediction algorithm. We analyzed the use of common home appliances (TV, computer, water purifier, microwave, washing machine, etc.) in a standard house and the power consumption reduction by the i-HEMS system. Through a total of six days of empirical experiments, before implementing i-HEMS, home appliances consumed 13,062 Wh. With i-HEMS, the total consumption was reduced to 10,434 Wh (a 20% reduction), with 9060 Wh attributed to home appliances and 1374 Wh to i-HEMS operation. [ABSTRACT FROM AUTHOR]

Electric motors play a fundamental role in various industries, and their relevance is strengthened in the context of the energy transition. Having efficient tools and techniques to detect and diagnose faults in electrical machines is crucial, as is providing early alerts to facilitate prompt decision-making. This study proposes indicators based on the magnitude of the space vector stator current for detecting and diagnosing incipient inter-turn short circuits (ITSCs) in induction motors (IMs). The effectiveness of these indicators was evaluated using four machine learning methods previously documented in the literature: random forests (RFs), support vector machines (SVMs), the k-nearest neighbor (kNN), and feedforward and recurrent neural networks (FNNs and RNNs). This assessment was conducted using experimental data. The results were compared with indicators based on discrete wavelet transform (DWT), demonstrating the viability of the proposed approach, which opens up a way of detecting incipient ITSCs in three-phase IMs. Furthermore, utilizing features derived from the magnitude of the spatial vector led to the successful identification of the phase affected by the fault. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HSIs) provide valuable spatial–spectral information for ground analysis. However, in few-shot (FS) scenarios, the limited availability of training samples poses significant challenges in capturing the sample distribution under diverse environmental conditions. Semi-supervised learning has shown promise in exploring the distribution of unlabeled samples through pseudo-labels. Nonetheless, FS HSI classification encounters the issue of high intra-class spectral variability and inter-class spectral similarity, which often lead to the diffusion of unreliable pseudo-labels during the iterative process. In this paper, we propose a simple yet effective progressive pseudo-label selection strategy that leverages the spatial–spectral consistency of HSI pixel samples. By leveraging spatially aligned ground materials as connected regions with the same semantic and similar spectrum, pseudo-labeled samples were selected based on round-wise confidence scores. Samples within both spatially and semantically connected regions of FS samples were assigned pseudo-labels and joined subsequent training rounds. Moreover, considering the spatial positions of FS samples that may appear in diverse patterns, to fully utilize unlabeled samples that fall outside the neighborhood of FS samples but still belong to certain connected regions, we designed a matching active learning approach for expert annotation based on the temporal confidence difference. We identified samples with the highest training value in specific regions, utilizing the consistency between predictive labels and expert labels to decide whether to include the region or the sample itself in the subsequent semi-supervised iteration. Experiments on both classic and more recent HSI datasets demonstrated that the proposed base model achieved SOTA performance even with extremely rare labeled samples. Moreover, the extended version with active learning further enhances performance by involving limited additional annotation. [ABSTRACT FROM AUTHOR]

Radiation-induced lung injury (RILI) is a dose-limiting toxicity for cancer patients receiving thoracic radiotherapy. As such, it is important to characterize metabolic associations with the early and late stages of RILI, namely pneumonitis and pulmonary fibrosis. Recently, Raman spectroscopy has shown utility for the differentiation of pneumonitic and fibrotic tissue states in a mouse model; however, the specific metabolite-disease associations remain relatively unexplored from a Raman perspective. This work harnesses Raman spectroscopy and supervised machine learning to investigate metabolic associations with radiation pneumonitis and pulmonary fibrosis in a mouse model. To this end, Raman spectra were collected from lung tissues of irradiated/non-irradiated C3H/HeJ and C57BL/6J mice and labelled as normal, pneumonitis, or fibrosis, based on histological assessment. Spectra were decomposed into metabolic scores via group and basis restricted non-negative matrix factorization, classified with random forest (GBR-NMF-RF), and metabolites predictive of RILI were identified. To provide comparative context, spectra were decomposed and classified via principal component analysis with random forest (PCA-RF), and full spectra were classified with a convolutional neural network (CNN), as well as logistic regression (LR). Through leave-one-mouse-out cross-validation, we observed that GBR-NMF-RF was comparable to other methods by measure of accuracy and log-loss (p > 0.10 by Mann–Whitney U test), and no methodology was dominant across all classification tasks by measure of area under the receiver operating characteristic curve. Moreover, GBR-NMF-RF results were directly interpretable and identified collagen and specific collagen precursors as top fibrosis predictors, while metabolites with immune and inflammatory functions, such as serine and histidine, were top pneumonitis predictors. Further support for GBR-NMF-RF and the identified metabolite associations with RILI was found as CNN interpretation heatmaps revealed spectral regions consistent with these metabolites. [ABSTRACT FROM AUTHOR]

Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands substantial time from clinical specialists. Addressing this issue, we introduce the S4MI (Self-Supervision and Semi-Supervision for Medical Imaging) pipeline, a novel approach that leverages advancements in self-supervised and semi-supervised learning. These techniques engage in auxiliary tasks that do not require labeling, thus simplifying the scaling of machine supervision compared to fully-supervised methods. Our study benchmarks these techniques on three distinct medical imaging datasets to evaluate their effectiveness in classification and segmentation tasks. Notably, we observed that self-supervised learning significantly surpassed the performance of supervised methods in the classification of all evaluated datasets. Remarkably, the semi-supervised approach demonstrated superior outcomes in segmentation, outperforming fully-supervised methods while using 50% fewer labels across all datasets. In line with our commitment to contributing to the scientific community, we have made the S4MI code openly accessible, allowing for broader application and further development of these methods. The code can be accessed at https://github.com/pranavsinghps1/S4MI. [ABSTRACT FROM AUTHOR]

Background: Coastal areas are subject to various anthropogenic and natural influences. In this study, we investigated and compared the characteristics of two coastal regions, Andhra Pradesh (AP) and Goa (GA), focusing on pollution, anthropogenic activities, and recreational impacts. We explored three main factors influencing the differences between these coastlines: The Bay of Bengal's shallower depth and lower salinity; upwelling phenomena due to the thermocline in the Arabian Sea; and high tides that can cause strong currents that transport pollutants and debris. Results: The microbial diversity in GA was significantly higher than that in AP, which might be attributed to differences in temperature, soil type, and vegetation cover. 16S rRNA amplicon sequencing and bioinformatics analysis indicated the presence of diverse microbial phyla, including candidate phyla radiation (CPR). Statistical analysis, random forest regression, and supervised machine learning models classification confirm the diversity of the microbiome accurately. Furthermore, we have identified 450 cultures of heterotrophic, biotechnologically important bacteria. Some strains were identified as novel taxa based on 16S rRNA gene sequencing, showing promising potential for further study. Conclusion: Thus, our study provides valuable insights into the microbial diversity and pollution levels of coastal areas in AP and GA. These findings contribute to a better understanding of the impact of anthropogenic activities and climate variations on biology of coastal ecosystems and biodiversity. [ABSTRACT FROM AUTHOR]

The joint analysis of two datasets X and Y that describe the same phenomena (e.g. the cellular state), but measure disjoint sets of variables (e.g. mRNA vs. protein levels) is currently challenging. Traditional methods typically analyze single interaction patterns such as variance or covariance. However, problem-tailored external knowledge may contain multiple different information about the interaction between the measured variables. We introduce MIASA, a holistic framework for the joint analysis of multiple different variables. It consists of assembling multiple different information such as similarity vs. association, expressed in terms of interaction-scores or distances, for subsequent clustering/classification. In addition, our framework includes a novel qualitative Euclidean embedding method (qEE-Transition) which enables using Euclidean-distance/vector-based clustering/classification methods on datasets that have a non-Euclidean-based interaction structure. As an alternative to conventional optimization-based multidimensional scaling methods which are prone to uncertainties, our qEE-Transition generates a new vector representation for each element of the dataset union X∪Y in a common Euclidean space while strictly preserving the original ordering of the assembled interaction-distances. To demonstrate our work, we applied the framework to three types of simulated datasets: samples from families of distributions, samples from correlated random variables, and time-courses of statistical moments for three different types of stochastic two-gene interaction models. We then compared different clustering methods with vs. without the qEE-Transition. For all examples, we found that the qEE-Transition followed by Ward clustering had superior performance compared to non-agglomerative clustering methods but had a varied performance against ultrametric-based agglomerative methods. We also tested the qEE-Transition followed by supervised and unsupervised machine learning methods and found promising results, however, more work is needed for optimal parametrization of these methods. As a future perspective, our framework points to the importance of more developments and validation of distance-distribution models aiming to capture multiple-complex interactions between different variables. [ABSTRACT FROM AUTHOR]

The ongoing expansion of human genomic datasets propels therapeutic target identification; however, extracting gene-disease associations from gene annotations remains challenging. Here, we introduce Mantis-ML 2.0, a framework integrating AstraZeneca's Biological Insights Knowledge Graph and numerous tabular datasets, to assess gene-disease probabilities throughout the phenome. We use graph neural networks, capturing the graph's holistic structure, and train them on hundreds of balanced datasets via a robust semi-supervised learning framework to provide gene-disease probabilities across the human exome. Mantis-ML 2.0 incorporates natural language processing to automate disease-relevant feature selection for thousands of diseases. The enhanced models demonstrate a 6.9% average classification power boost, achieving a median receiver operating characteristic (ROC) area under curve (AUC) score of 0.90 across 5220 diseases from Human Phenotype Ontology, OpenTargets, and Genomics England. Notably, Mantis-ML 2.0 prioritizes associations from an independent UK Biobank phenome-wide association study (PheWAS), providing a stronger form of triaging and mitigating against underpowered PheWAS associations. Results are exposed through an interactive web resource. [ABSTRACT FROM AUTHOR]