Similar Features Research Articles

Transfer learning integrating similarity analysis for short-term and long-term building energy consumption prediction

Currently, building energy consumption prediction models are usually based on a large amount of historical operational data in high demands of building operating hours and monitoring systems. However, many buildings may lack operational data due to relatively limited monitoring systems, causing the failure to use data-driven methods to characterize the energy profile. In this context, transfer learning is a promising method to establish the knowledge transfer between many high-quality building operation datasets and a small amount of target building data, and to help predict energy consumption in the target building. This paper studies the possibility of employing transfer learning to achieve both short and long-term building energy consumption prediction. Firstly, a similarity analysis method, based on variable modal decomposition and dynamic time warping, is proposed for identifying the source buildings with the most similar energy features to the target building. Then, transfer learning for long-term prediction air-conditioning energy consumption is developed with weather parameters generated by the Morphing method as inputs. For the short-term single-step prediction, the proposed model CV-RMSE improves 81.3% (AEC) and 77.4% (EEC), respectively, compared to the prediction model that does not implement the transfer learning strategy and directly uses the target BEC data. As for the short-term multi-step prediction, the proposed model CV-RMSE improves 62.0% (AEC) and 65.5% (EEC), respectively. For the long-term prediction, the average CV-RMSE for the whole year is 6.62% and 11.15% for the proposed and directly target domain-based model, respectively. The proposed method explores the practicality of transfer learning in building energy forecasting, contributing to the use of existing building operation data for energy management at different timespan.

Differentiation Between Invasive Adenocarcinoma and Focal Interstitial Fibrosis among Persistent Pulmonary Part-solid Nodules: With Emphasis on the CT Morphologic Analysis.

Focal interstitial fibrosis (FIF) manifesting as a persistent part-solid nodule (PSN) has been mistakenly treated surgically due to similar imaging features to invasive adenocarcinoma (ADC). The purpose of this study was to observe predictive imaging features correlated with FIF through CT morphologic analysis. From January 2009 to December 2020, 44 patients with surgically proven FIF in a single institution were enrolled and compared with 88 ADC patients through propensity score matching. Patient characteristics and CT morphologic analysis of persistent PSNs were used to identify predictive imaging features of FIF. Receiver operating characteristic (ROC) curve analysis was used to quantify the performance of imaging features. A total of 132 patients with 132 PSNs (44 FIF, 88 ADC; mean age, 67.7±7.58; 75 females) were involved in our analysis. Multivariable analysis demonstrated that preserved peritumoral vascular margin (preserved vascular margin), preserved secondary pulmonary lobule margin (preserved lobular margin), and lower coronal to axial ratio (C/A ratio; cutoff: 1.005) were significant independent predictors of FIF (P<0.05). ROC curve analysis to evaluate the predictive value of the logistic model based on the imaging features of FIF, and the AUC value was 0.881. CT imaging features of preserved vascular margin, preserved lobular margin, and lower C/A ratio (cutoff, <1.005) might be helpful imaging features in discriminating FIF over ADC among persistent PSN in clinical practice.

Personalized and privacy-preserving federated graph neural network

High-performance GNN obtains dependencies within a graph by capturing the mechanism of message passing and aggregation between neighboring nodes in the graph, and successfully updates node embeddings. However, in practical applications, the inherent model structure of the graph is highly susceptible to privacy attacks, and the heterogeneity of external data can lead to a decrease in model performance. Motivated by this challenge, this work proposes a novel framework called Personalized Federated Graph Neural Network for Privacy-Preserving (PFGNN). Specifically, firstly, this work introduces a graph similarity strategy. Based on the principle that clients with similar features exhibit stronger homophily, this work divides all participating clients into multiple clusters for collaborative training. Furthermore, within each group, this work employs an attention mechanism to design a federated aggregation weighting scheme. This scheme is used to construct a global model on the server, which helps mitigate the difficulty of model generalization resulting from data heterogeneity collected from different clients. Lastly, to ensure the privacy of model parameters during the training process and prevent malicious adversaries from stealing them, this work implements privacy-enhancing technology by introducing an optimized function-hiding multi-input function encryption scheme. This ensures the security of both model data and user privacy. Experiments on real datasets show that our scheme outperforms FedAvg in accuracy, and the communication overhead is linearly related to the number of clients. Through this framework, PFGNN can handle all kinds of non-Euclidean structured data, multiple clients collaborate to train high-quality and highly secure global models. This work provides the foundation for designing efficient and privacy-preserving personalized federated graph neural networks.

Data-driven internal mobility: Similarity regularization gets the job done

This paper presents a novel approach to support career management by recommending job–employee matches within an organization through data-driven insights. We build a recommender system to propose matches. The presented approach extends upon a conventional collaborative filtering recommender system, which suggests matches based on the historic performance similarities of employees. To address the prevalent challenge of the cold start issue in internal placement, we incorporate personal employee data with a similarity-based regularization term. This regularization term finds latent representations that are closer to each other when employees share similar personal features. This approach is evaluated using three real-life datasets and demonstrates a highly competitive performance compared to state-of-the-art benchmark methods. Overall, we make three contributions to the field of HR analytics: (i) we present a comprehensive survey of job–employee recommender systems in the context of internal mobility, (ii) we implement a similarity regularization method, and (iii) we release a first-of-its-kind HR dataset on internal mobility. All code and public data used in this study are available on GitHub.

Clustering of small watersheds in hilly areas based on complex network theory and similarity analysis

ABSTRACT Clustering analysis of small watersheds is an effective tool for identifying the similarity of runoff generation and concentration. In this paper, 545 small watersheds in the hilly areas of Shandong Province were investigated, and 12 indicators representing their climate and subsurface characteristics were selected to identify communities based on hydrological similarity. We further analyzed the hydrological connections among the small watersheds within each community using three indicators (network mean, centrality, and k-core). Finally, the clustering results were evaluated on the basis of the small watershed flood peak modulus. The results of this complex network method indicate that the study area contained six large communities and nine small communities. The community-clustering results were reasonable and showed the interconnectedness of the watersheds within each community. The three network indicators adequately described the degree of similarity, the representativeness of the watersheds, and the spatial scales of similar hydrological features. This method should be helpful for addressing the issue of parameter transplantation in ungauged watersheds and implementation of a flood risk management strategy.

Evaluating an extraction-free sample preparation method for multiplex detection of SARS-Cov-2, influenza A/B, and RSV with implementation on a microfluidic chip

Following the relaxation of COVID-19 restrictions, other respiratory viruses such as influenza and respiratory syncytial virus (RSV), whose transmission were decreased due to COVID-19 precautions, are rising again. Because of similar clinical features and reported co-infections, multiplex detection of SARS-CoV-2, influenza A/B, and RSV is required to use specific treatments. This study assessed an extraction-free sample preparation (heat treatment at 95°C for 3 minutes) for multiplex detection using rRT-PCR. Despite an observed Ct-delay (∆Ct) averageing 1.26 compared to the standard method, an acceptable total sensitivity of 92 % and a negative predictive value (NPV) of 96 % were obtained. Moreover, Implementation on a microfluidic chip demonstrated efficiency, maintaining an excellent correlation (R2=0.983) with the standard method. Combining this extraction-free procedure with rRT-PCR on a microfluidic chip seems promising, because it simplifies the design and reduces the cost and complexity of the integrated assay for multiplex detection of SARS-CoV-2, influenza A/B, and RSV.

Holocene records of oyster reefs in a shallow semi-enclosed island embayment of the Aegean Sea

A high-resolution survey in the semi-enclosed Kalloni Gulf (Lesvos Island, NE Aegean Sea) revealed a plethora of oyster reef structures. The reefs have a relief of up to 6 m high and a length of 1.4 km at the deepest part (∼17 m) of the surveyed area and are developed in a fine-grained seabed. Acoustic backscatter variations caused by the presence and the type/distribution of different reef structures were mapped, resulting in the identification of four backscatter types. Sub-bottom acoustic information revealed the presence of similar buried features, which were classified in three types according to their characteristics. The seismic stratigraphy also showed the Holocene highstand and the transgressive system tracts as well as a deeper-seated distinct erosional surface with numerous buried channels, most likely corresponding to the surface flooded during the Holocene marine transgression. Starting at around 9700 years BP, the Kalloni paleo-landscape was progressively submerged and gradually transformed into a shallow, land-locked marine environment, allowing the establishment, and thriving of oyster reefs. The buried reefs presumably began to grow during the early stages of the gulf's transgression, whereas most of the modern reefs were developed/maintained by the modern hydrodynamic/sedimentary regime. It is the first time that such a large occurrence of well developed, diachronic oyster reef assemblage has been documented in the transgressive coastal environments of the microtidal Mediterranean Sea, but further research is required to determine the exact mode of their development.

Investigation of some finite integrals incorporating incomplete Aleph functions

In this paper, we introduce a new approach to the study of finite integral formulas associated with special functions, bringing out the incomplete Aleph functions and other well-known special functions. Our method is based on the finite integral operator applied to incomplete Aleph functions. This approach makes it easier to derive integral formulas that connect the incomplete Aleph functions using well-known special functions and algebraic expressions. As a result, we can group integral formulas and special functions into different classes according to similar features. Furthermore, we can discover new integral formulas with this framework that are useful for computational applications.

Uncertain prediction of deformable image registration on lung CT using multi-category features and supervised learning.

The assessment of deformable registration uncertainty is an important task for the safety and reliability of registration methods in clinical applications. However, it is typically done by a manual and time-consuming procedure. We propose a novel automatic method to predict registration uncertainty based on multi-category features and supervised learning. Three types of features, including deformation field statistical features, deformation field physiologically realistic features, and image similarity features, are introduced and calculated to train the random forest regressor for local registration uncertain prediction. Deformation field statistical features represent the numerical stability of registration optimization, which are correlated to the uncertainty of deformation fields; deformation field physiologically realistic features represent the biomechanical properties of organ motions, which mathematically reflect the physiological reality of deformation; image similarity features reflect the similarity between the warped image and fixed image. The multi-category features comprehensively reflect the registration uncertainty. The strategy of spatial adaptive random perturbations is also introduced to accurately simulate spatial distribution of registration uncertainty, which makes deformation field statistical features more discriminative to the uncertainty of deformation fields. Experiments were conducted on three publicly available thoracic CT image datasets. Seventeen randomly selected image pairs are used to train the random forest model, and 9 image pairs are used to evaluate the prediction model. The quantitative experiments on lung CT images show that the proposed method outperforms the baseline method for uncertain prediction of classical iterative optimization-based registration and deep learning-based registration with different registration qualities. The proposed method achieves good performance for registration uncertain prediction, which has great potential in improving the accuracy of registration uncertain prediction.

An efficient lightweight network for image denoising using progressive residual and convolutional attention feature fusion

While deep learning has become the go-to method for image denoising due to its impressive noise removal capabilities, excessive network depth often plagues existing approaches, leading to significant computational burdens. To address this critical bottleneck, we propose a novel lightweight progressive residual and attention mechanism fusion network that effectively alleviates these limitations. This architecture tackles both Gaussian and real-world image noise with exceptional efficacy. Initiated through dense blocks (DB) tasked with discerning the noise distribution, this approach substantially reduces network parameters while comprehensively extracting local image features. The network then adopts a progressive strategy, whereby shallow convolutional features are incrementally integrated with deeper features, establishing a residual fusion framework adept at extracting encompassing global features relevant to noise characteristics. The process concludes by integrating the output feature maps from each DB and the robust edge features from the convolutional attention feature fusion module (CAFFM). These combined elements are then directed to the reconstruction layer, ultimately producing the final denoised image. Empirical analyses conducted in environments characterized by Gaussian white noise and natural noise, spanning noise levels 15–50, indicate a marked enhancement in performance. This assertion is quantitatively corroborated by increased average values in metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Feature Similarity Index for Color images (FSIMc), outperforming the outcomes of more than 20 existing methods across six varied datasets. Collectively, the network delineated in this research exhibits exceptional adeptness in image denoising. Simultaneously, it adeptly preserves essential image features such as edges and textures, thereby signifying a notable progression in the domain of image processing. The proposed model finds applicability in a range of image-centric domains, encompassing image processing, computer vision, video analysis, and pattern recognition.

Cross and local optimal avoidance of RIME algorithm: A segmentation study for COVID-19 X-ray images

Image segmentation is a crucial technique in analyzing X-ray medical images as it aids in uncovering relevant information concealed within a patient's body, a pivotal aspect of the diagnostic process. The effectiveness of computer-aided diagnosis systems largely depends on the accuracy of the image processing methods. In recent years, multi-threshold image segmentation methods have found widespread application in medical image analysis. Despite the effectiveness of some renowned methods for binary threshold segmentation, the field still faces challenges due to the high cost of threshold computation. Metaheuristic algorithms hold the potential to address this issue as they can produce sufficiently reasonable solutions with manageable computational overheads. While some similar methods have been proposed, the imbalance between exploration and exploitation results in instability as the number of thresholds increases. Consequently, these solutions suffer from reduced efficiency in computing thresholds. In this study, a variant of the latest RIME algorithm, termed SLCRIME, is proposed. This paper replaces the pseudo-random method with low-discrepancy Sobol sequences for solution initialization. Additionally, two methods aimed at avoiding local optima and promoting information exchange within the solution set are introduced, further enhancing its capability to search for optimal threshold sets for IS systems. Subsequently, a multi-threshold image segmentation model based on SLCRIME is proposed and applied to segment 6 COVID-19 X-ray images. In the experiments, SLCRIME is compared with 6 peer algorithms, and the results are evaluated using image segmentation accuracy, feature similarity index metrics (FSIM), peak signal-to-noise ratio (PSNR), and structural similarity index metrics (SSIM). The analysis indicates that SLCRIME achieves optimal thresholds at reasonable computational costs and outperforms other algorithms in terms of performance.

Advanced Sparse Filtering-Based Domain Adaptation for Fault Diagnosis in Variable Working Conditions

Traditional domain adaptation (DA) methods often encounter challenges with cross-domain feature extraction and the precise assessment of domain differences. To overcome these limitations, we introduce the Enhanced Sparse Filtering-Based Domain Adaptation (ESFBDA) method. This method distinguishes itself by enhancing sparse filtering (SF) with the integration of row-column normalization and a cosine penalty, specifically designed to minimize feature loss—a critical issue in existing DA techniques. Additionally, we employ Bootstrap resampling to refine domain distribution alignment, a novel step that boosts feature similarity and effectiveness in DA. This integrated approach ensures more accurate feature extraction, which is crucial for the classifier's fault detection capability. In our study, through two distinct experiments on Electro-Hydrostatic Actuator (EHA) internal leakage and bearing fault diagnosis, the ESFBDA method demonstrated remarkable accuracy, significantly surpassing traditional approaches and showcasing its robust applicability across varied diagnostic scenarios.

Whole-body muscle magnetic resonance imaging in inflammatory myopathy with mitochondrial pathology.

Inflammatory myopathy with mitochondrial pathology (IM-Mito) is a rare condition described in a few case series, and it is not clear whether it is a specific disease or a variant of Inclusion Body Myositis (IBM). Radiological data of IM-Mito patients has only been evaluated in one study. To analyze whole-body muscle magnetic resonance imaging (MRI) features in patients with IM-Mito compared with individuals with IBM. Fourteen IM-Mito and ten IBM patients were included. IM-Mito was defined by endomysial inflammatory infiltrate, presence of at least 1% of Cytochrome C Oxidase negative fibers, and absence of rimmed vacuoles in muscle biopsy; and IBM was defined by the presence of dystrophic muscular abnormalities, endomysial inflammatory infiltrate, and rimmed vacuoles. Patients underwent clinical evaluation and whole-body muscle MRI to determine the presence of edema, and fatty infiltration in various muscles. Muscle imaging abnormalities were asymmetric in most patients with IM-Mito and IBM. Muscles with the highest average degree of fatty infiltration in both conditions were the quadriceps and medial gastrocnemius. Most patients with IM-Mito and IBM showed imaging patterns of rectus femoris relatively spared compared to other quadriceps muscles. The flexor digitorum profundus was the most affected muscle of the upper limbs in both IBM and IM-Mito. Although the results suggest some similarities in muscle imaging features between IM-Mito and IBM, there remains uncertainty whether these two conditions are part of the same clinical spectrum.

Discrimination and screening of volatile metabolites in atractylodis rhizoma from different varieties using headspace solid-phase microextraction-gas chromatography-mass spectrometry and headspace gas chromatography-ion mobility spectrometry, and ultra-fast gas chromatography electronic nose

Atractylodis rhizoma is a common bulk medicinal material with multiple species. Although different varieties of atractylodis rhizoma exhibit variations in their chemical constituents and pharmacological activities, they have not been adequately distinguished due to their similar morphological features. Hence, the purpose of this research is to analyze and characterize the volatile organic compounds (VOCs) in samples of atractylodis rhizoma using multiple techniques and to identify the key differential VOCs among different varieties of atractylodis rhizoma for effective discrimination. The identification of VOCs was carried out using headspace solid-phase microextraction-gas chromatography-mass spectrometry (HS-SPME-GC–MS) and headspace gas chromatography-ion mobility spectrometry (HS-GC-IMS), resulting in the identification of 60 and 53 VOCs, respectively. The orthogonal partial least squares discriminant analysis (OPLS-DA) model was employed to screen potential biomarkers and based on the variable importance in projection (VIP ≥ 1.2), 24 VOCs were identified as critical differential compounds. Random forest (RF), K-nearest neighbor (KNN) and back propagation neural network based on genetic algorithm (GA-BPNN) models based on potential volatile markers realized the greater than 90 % discriminant accuracies, which indicates that the obtained key differential VOCs are reliable. At the same time, the aroma characteristics of atractylodis rhizoma were also analyzed by ultra-fast gas chromatography electronic nose (Ultra-fast GC E-nose). This study indicated that the integration of HS-SPME-GC–MS, HS-GC-IMS and ultra-fast GC E-nose with chemometrics can comprehensively reflect the differences of VOCs in atractylodis rhizoma samples from different varieties, which will be a prospective tool for variety discrimination of atractylodis rhizoma.

Chatbots, search engines, and the sealing of knowledges

AbstractIn 2023, online search engine provider Microsoft integrated a language model that provides direct answers to search queries into its search engine Bing. Shortly afterwards, Google also introduced a similar feature to its search engine with the launch of Google Gemini. This introduction of direct answers to search queries signals an important and significant change in online search. This article explores the implications of this new search paradigm. Drawing on Donna Haraway’s theory of Situated Knowledges and Rainer Mühlhoff’s concept of Sealed Surfaces, I introduce the term Sealed Knowledges to draw attention to the increasingly difficult access to the plurality of potential answers to search queries through the output of a singular, authoritative, and plausible text paragraph. I argue that the integration of language models for the provision of direct answers into search engines is based on a de-situated and disembodied understanding of knowledge and affects the subjectivities of its users. At the same time, the sealing of knowledges can lead to an increasing spread of misinformation and may make marginalized knowledge increasingly difficult to find. The paper concludes with an outlook on how to resist the increasing sealing of knowledges in online search.

S2CANet: A self-supervised infrared and visible image fusion based on co-attention network

Existing methods for infrared and visible image fusion (IVIF) often overlook the analysis of common and distinct features among source images. Consequently, this study develops A self-supervised infrared and visible image fusion based on co-attention network, incorporating auxiliary networks and backbone networks in its design. The primary concept is to transform both common and distinct features into common features and reconstructed features, subsequently deriving the distinct features through their subtraction. To enhance the similarity of common features, we designed the fusion block based on co-attention (FBC) module specifically for this purpose, capturing common features through co-attention. Moreover, fine-tuning the auxiliary network enhances the image reconstruction effectiveness of the backbone network. It is noteworthy that the auxiliary network is exclusively employed during training to guide the self-supervised completion of IVIF by the backbone network. Additionally, we introduce a novel estimate for weighted fidelity loss to guide the fused image in preserving more brightness from the source image. Experiments conducted on diverse benchmark datasets demonstrate the superior performance of our S2CANet over state-of-the-art IVIF methods.

Effect of melt temperature on the quasi-equilibrium solidification of K465 Ni-based superalloy

The solidification process of Ni-based superalloy K465 was examined using DTA and X-ray diffraction. The impact of melt structure on solidification process and the morphology of MC carbide and γ′-phase was analyzed. It was observed that an increase in melt peak temperature led to a significant decrease in precipitation temperature for carbides, but only a slight increase in the formation temperature of matrix and eutectic microstructure. The X-ray diffraction results showed that some ordered structures were detected in the sample with melt peak temperature of 1450 °C and 1500 °C, but not in the sample with melt peak temperature of 1360 °C. Furthermore, the ordered structure displayed similar crystalline features with M6C carbide. As the melt peak temperature increased, the carbides changed from block type to script type morphology. This phenomenon was likely caused by the formation of ordered structures at high temperatures. However, the microstructure of γ matrix and γ′ precipitates remained unaffected by the melt peak temperature.

Low-dose CT reconstruction based on high-dimensional partial differential equation projection recovery

We propose a low-dose CT reconstruction method using partial differential equation (PDE) denoising under high-dimensional constraints. The projection data were mapped into a high-dimensional space to construct a high-dimensional representation of the data, which were updated by moving the points in the high-dimensional space. The data were denoised using partial differential equations and the CT image was reconstructed using the FBP algorithm. Compared with those by FBP, PWLS-QM and TGV-WLS methods, the relative root mean square error of the Shepp-Logan image reconstructed by the proposed method were reduced by 68.87%, 50.15% and 27.36%, the structural similarity values were increased by 23.50%, 8.83% and 1.62%, and the feature similarity values were increased by 17.30%, 2.71% and 2.82%, respectively. For clinical image reconstruction, the proposed method, as compared with FBP, PWLS-QM and TGV-WLS methods, resulted in reduction of the relative root mean square error by 42.09%, 31.04% and 21.93%, increased the structural similarity values by 18.33%, 13.45% and 4.63%, and increased the feature similarity values by 3.13%, 1.46% and 1.10%, respectively. The new method can effectively reduce the streak artifacts and noises while maintaining the spatial resolution in reconstructed low-dose CT images.

An improved deep hashing model for image retrieval with binary code similarities

The exponential growth of data raises an unprecedented challenge in data analysis: how to retrieve interesting information from such large-scale data. Hash learning is a promising solution to address this challenge, because it may bring many potential advantages, such as extremely high efficiency and low storage cost, after projecting high-dimensional data to compact binary codes. However, traditional hash learning algorithms often suffer from the problem of semantic inconsistency, where images with similar semantic features may have different binary codes. In this paper, we propose a novel end-to-end deep hashing method based on the similarities of binary codes, dubbed CSDH (Code Similarity-based Deep Hashing), for image retrieval. Specifically, it extracts deep features from images to capture semantic information using a pre-trained deep convolutional neural network. Additionally, a hidden and fully connected layer is attached at the end of the deep network to derive hash bits by virtue of an activation function. To preserve the semantic consistency of images, a loss function has been introduced. It takes the label similarities, as well as the Hamming embedding distances, into consideration. By doing so, CSDH can learn more compact and powerful hash codes, which not only can preserve semantic similarity but also have small Hamming distances between similar images. To verify the effectiveness of CSDH, we evaluate CSDH on two public benchmark image collections, i.e., CIFAR-10 and NUS-WIDE, with five classic shallow hashing models and six popular deep hashing ones. The experimental results show that CSDH can achieve competitive performance to the popular deep hashing algorithms.

Supplementation of deep neural networks with simplified physics-based features to increase accuracy of plate fundamental frequency predictions

To improve predictive machine learning-based models limited by sparse data, supplemental physics-related features are introduced into a deep neural network (DNN). While some approaches inject physics through differential equations or numerical simulation, improvements are possible using simplified relationships from engineering references. To evaluate this hypothesis, thin rectangular plates were simulated to generate training datasets. With plate dimensions and material properties as input features and fundamental natural frequency as the output, predictive performance of a data-driven DNN-based model is compared with models using supplemental inputs, such as modulus of rigidity. To evaluate model accuracy improvements, these additional features are injected into various DNN layers, and the network is trained with four different dataset sizes. When evaluated against independent data of similar features to the training sets, supplementation provides no statistically-significant prediction error reduction. However, notable accuracy gains occur when independent test data is of material and dimensions different from the original training set. Furthermore, when physics-enhanced data is injected into multiple DNN layers, reductions in mean error from 33.2% to 19.6%, 34.9% to 19.9%, 35.8% to 22.4%, and 43.0% to 28.4% are achieved for dataset sizes of 261, 117, 60, and 30, respectively, demonstrating potential for generalizability using a data supplementation approach. Additionally, when compared with other methods—such as linear regression and support vector machine (SVM) approaches—the physics-enhanced DNN demonstrates an order of magnitude reduction in percentage error for dataset sizes of 261, 117, and 60 and a 30% reduction for a size of 30 when compared with a cubic SVM model independently tested with data divergent from the training and validation set.