Search

Missing data imputation is a key topic in healthcare that covers the issues and strategies involved in dealing with partial data in medical records, clinical trials, and health surveys. Data in healthcare might be missing for a variety of reasons, including non-response in surveys, data entry problems, or unrecorded information during therapeutic appointments. This paper introduces a novel approach to impute missing data utilizing a hybrid model that integrates denoising autoencoders with generative adversarial networks (GANs). We begin by highlighting the prevalence of missing data in health care datasets and the potential impact on analytical outcomes. The proposed methodology leverages the denoising autoencoder's ability to reconstruct data from noisy inputs, coupled with the GAN's proficiency in generating synthetic data that is indistinguishable from real data. By combining these two neural network architectures, our model demonstrates an enhanced capability to predict and fill in missing data points effectively. To validate our approach, we conducted experiments on several large-scale health care datasets with varying degrees of artificially introduced missingness. The performance of our model was benchmarked against traditional imputation methods such as mean imputation and k-nearest neighbors, as well as against standalone denoising autoencoders and GANs. Our results indicate a significant improvement in imputation accuracy, as measured by root mean square error (RMSE) and mean absolute error (MAE), confirming the efficacy of the hybrid model in handling missing data in a robust manner. [ABSTRACT FROM AUTHOR]

Cognitive scientists and neuroscientists typically understand the brain as a complex communication/information-processing system. A limitation of this framework is that it requires cognitive systems to have prior knowledge about their environment to successfully perform some of their basic functions, such as perceiving. It is unclear how the source of such knowledge can be explained from within this framework. Drawing on Dennett (1981), we refer to this as the loans of intelligence problem. Recent advances in machine learning have resulted in the development of a family of algorithms, including the class known as autoencoders, that seem to provide a way for the information-processing framework to avoid this problem: cognitive systems do not require loans of intelligence, but instead acquire the knowledge necessary for perception through a process of unsupervised learning. This paper argues that although autoencoders do avoid the loans of intelligence problem, how they do so should not be understood from within the information-processing framework. Instead, their success should be interpreted as a proof of concept of how neural networks can attune to Gibsonian information. We thus propose that autoencoders belong to a class of algorithms for modeling the brain that have recently been dubbed direct fit algorithms. [ABSTRACT FROM AUTHOR]

The recent advances in high-throughput single-cell sequencing have created an urgent demand for computational models which can address the high complexity of single-cell multiomics data. Meticulous single-cell multiomics integration models are required to avoid biases towards a specific modality and overcome sparsity. Batch effects obfuscating biological signals must also be taken into account. Here, we introduce a new single-cell multiomics integration model, Single-cell Multiomics Autoencoder Integration (scMaui) based on variational product-of-experts autoencoders and adversarial learning. scMaui calculates a joint representation of multiple marginal distributions based on a product-of-experts approach which is especially effective for missing values in the modalities. Furthermore, it overcomes limitations seen in previous VAE-based integration methods with regard to batch effect correction and restricted applicable assays. It handles multiple batch effects independently accepting both discrete and continuous values, as well as provides varied reconstruction loss functions to cover all possible assays and preprocessing pipelines. We demonstrate that scMaui achieves superior performance in many tasks compared to other methods. Further downstream analyses also demonstrate its potential in identifying relations between assays and discovering hidden subpopulations. [ABSTRACT FROM AUTHOR]

Research in the field of malware detection is currently leaning toward methods based on artificial intelligence algorithms due to the increasing limitations of traditional detection methods and the increasing accuracy of these methods. This study therefore introduces a novel approach to malware detection. This method integrates a deep learning model's autoencoder network with a grayscale graphic depiction of malware. By looking at the autoencoder's reconstruction error, we may assess if the grey-scale picture approach is feasible to use for malware detection. Additionally, it differentiates between malicious and safe software by utilizing the autoencoder's dimensionality reduction capabilities. Using the Android dataset, our newly introduced detection model attained a 95% accuracy and maintained a consistently high F-score of approximately 95% This outperformed more conventional methods of machine learning detection. [ABSTRACT FROM AUTHOR]

This work establishes a different paradigm on digital molecular spaces and their efficient navigation by exploiting sigma profiles. To do so, the remarkable capability of Gaussian processes (GPs), a type of stochastic machine learning model, to correlate and predict physicochemical properties from sigma profiles is demonstrated, outperforming state-of-the-art neural networks previously published. The amount of chemical information encoded in sigma profiles eases the learning burden of machine learning models, permitting the training of GPs on small datasets which, due to their negligible computational cost and ease of implementation, are ideal models to be combined with optimization tools such as gradient search or Bayesian optimization (BO). Gradient search is used to efficiently navigate the sigma profile digital space, quickly converging to local extrema of target physicochemical properties. While this requires the availability of pretrained GP models on existing datasets, such limitations are eliminated with the implementation of BO, which can find global extrema with a limited number of iterations. A remarkable example of this is that of BO toward boiling temperature optimization. Holding no knowledge of chemistry except for the sigma profile and boiling temperature of carbon monoxide (the worst possible initial guess), BO finds the global maximum of the available boiling temperature dataset (over 1,000 molecules encompassing more than 40 families of organic and inorganic compounds) in just 15 iterations (i.e., 15 property measurements), cementing sigma profiles as a powerful digital chemical space for molecular optimization and discovery, particularly when little to no experimental data is initially available. [ABSTRACT FROM AUTHOR]

Studies on the neural correlates of navigation in 3D environments are plagued by several issues that need to be solved. For example, experimental studies show markedly different place cell responses in rats and bats, both navigating in 3D environments. In this study, we focus on modelling the spatial cells in rodents in a 3D environment. We propose a deep autoencoder network to model the place and grid cells in a simulated agent navigating in a 3D environment. The input layer to the autoencoder network model is the HD layer, which encodes the agent's HD in terms of azimuth (θ) and pitch angles (ϕ). The output of this layer is given as input to the Path Integration (PI) layer, which computes displacement in all the preferred directions. The bottleneck layer of the autoencoder model encodes the spatial cell-like responses. Both grid cell and place cell-like responses are observed. The proposed model is verified using two experimental studies with two 3D environments. This model paves the way for a holistic approach using deep neural networks to model spatial cells in 3D navigation. [ABSTRACT FROM AUTHOR]

Marker-less hand–eye calibration permits the acquisition of an accurate transformation between an optical sensor and a robot in unstructured environments. Single monocular cameras, despite their low cost and modest computation requirements, present difficulties for this purpose due to their incomplete correspondence of projected coordinates. In this work, we introduce a hand–eye calibration procedure based on the rotation representations inferred by an augmented autoencoder neural network. Learning-based models that attempt to directly regress the spatial transform of objects such as the links of robotic manipulators perform poorly in the orientation domain, but this can be overcome through the analysis of the latent space vectors constructed in the autoencoding process. This technique is computationally inexpensive and can be run in real time in markedly varied lighting and occlusion conditions. To evaluate the procedure, we use a color-depth camera and perform a registration step between the predicted and the captured point clouds to measure translation and orientation errors and compare the results to a baseline based on traditional checkerboard markers. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) ensures the safety and reliability of civil infrastructure. Autoencoders, as unsupervised learning models, offer promise for SHM by learning data features and reducing dimensionality. However, comprehensive studies comparing autoencoder models in SHM are scarce. This study investigates the effectiveness of four autoencoder-based methodologies, combined with Hotelling's T 2 statistical tool, to detect and quantify structural changes in three civil engineering structures. The methodologies are evaluated based on computational costs and their abilities to identify structural anomalies accurately. Signals from the structures, collected by accelerometers, feed the autoencoders for unsupervised classification. The latent layer values of the autoencoders are used as parameters in Hotelling's T 2 , and results are compared between classes to assess structural changes. Average execution times of each model were calculated for computational efficiency. Despite variations, computational cost did not hinder any methodology. The study demonstrates that the best fitting model, VAE- T 2 , outperforms its counterparts in identifying and quantifying structural changes. While the AE, SAE, and CAE models showed limitations in quantifying changes, they remain relevant for detecting anomalies. Continuous application and development of these techniques contribute to SHM advancements, enabling the increased safety, cost-effectiveness, and long-term durability of civil engineering structures. [ABSTRACT FROM AUTHOR]

This study presents a novel approach that employs autoencoders (AE)—an artificial neural network—for the nonlinear transformation of time series to a compact latent space for efficient fuzzy clustering. The method was tested on atmospheric sea level pressure (SLP) data towards fuzzy clustering of atmospheric circulation types (CTs). CTs are a group of dates with a similar recurrent SLP spatial pattern. The analysis aimed to explore the effectiveness of AE in producing and improving the characterization of known CTs (i.e., recurrent SLP patterns) derived from traditional linear models like principal component analysis (PCA). After applying both PCA and AE for the linear and nonlinear transformation of the SLP time series, respectively, followed by a fuzzy clustering of the daily SLP time series from each technique, the resulting CTs generated by each method were compared to assess consistency. The findings reveal consistency between the SLP spatial patterns from the two methods, with 58% of the patterns showing congruence matches greater than 0.94. However, when examining the correctly classified dates (i.e., the true positives) using a threshold of 0.8 for the congruence coefficient between the spatial composite map representing the CT and the dates grouped under the CT, AE outperformed PCA with an average improvement of 29.2%. Hence, given AE's flexibility and capacity to model complex nonlinear relationships, this study suggests that AE could be a potent tool for enhancing fuzzy time series clustering, given its capability to facilitate the correct identification of dates when a given CT occurred and assigning the dates to the associated CT. [ABSTRACT FROM AUTHOR]

Abstract The recent advances in high-throughput single-cell sequencing have created an urgent demand for computational models which can address the high complexity of single-cell multiomics data. Meticulous single-cell multiomics integration models are required to avoid biases towards a specific modality and overcome sparsity. Batch effects obfuscating biological signals must also be taken into account. Here, we introduce a new single-cell multiomics integration model, Single-cell Multiomics Autoencoder Integration (scMaui) based on variational product-of-experts autoencoders and adversarial learning. scMaui calculates a joint representation of multiple marginal distributions based on a product-of-experts approach which is especially effective for missing values in the modalities. Furthermore, it overcomes limitations seen in previous VAE-based integration methods with regard to batch effect correction and restricted applicable assays. It handles multiple batch effects independently accepting both discrete and continuous values, as well as provides varied reconstruction loss functions to cover all possible assays and preprocessing pipelines. We demonstrate that scMaui achieves superior performance in many tasks compared to other methods. Further downstream analyses also demonstrate its potential in identifying relations between assays and discovering hidden subpopulations.

Abstract Studies on the neural correlates of navigation in 3D environments are plagued by several issues that need to be solved. For example, experimental studies show markedly different place cell responses in rats and bats, both navigating in 3D environments. In this study, we focus on modelling the spatial cells in rodents in a 3D environment. We propose a deep autoencoder network to model the place and grid cells in a simulated agent navigating in a 3D environment. The input layer to the autoencoder network model is the HD layer, which encodes the agent’s HD in terms of azimuth (θ) and pitch angles (ϕ). The output of this layer is given as input to the Path Integration (PI) layer, which computes displacement in all the preferred directions. The bottleneck layer of the autoencoder model encodes the spatial cell-like responses. Both grid cell and place cell-like responses are observed. The proposed model is verified using two experimental studies with two 3D environments. This model paves the way for a holistic approach using deep neural networks to model spatial cells in 3D navigation.

Deep Learning is having a remarkable impact on the design of Reduced Order Models (ROMs) for Partial Differential Equations (PDEs), where it is exploited as a powerful tool for tackling complex problems for which classical methods might fail. In this respect, deep autoencoders play a fundamental role, as they provide an extremely flexible tool for reducing the dimensionality of a given problem by leveraging on the nonlinear capabilities of neural networks. Indeed, starting from this paradigm, several successful approaches have already been developed, which are here referred to as Deep Learning-based ROMs (DL-ROMs). Nevertheless, when it comes to stochastic problems parameterized by random fields, the current understanding of DL-ROMs is mostly based on empirical evidence: in fact, their theoretical analysis is currently limited to the case of PDEs depending on a finite number of (deterministic) parameters. The purpose of this work is to extend the existing literature by providing some theoretical insights about the use of DL-ROMs in the presence of stochasticity generated by random fields. In particular, we derive explicit error bounds that can guide domain practitioners when choosing the latent dimension of deep autoencoders. We evaluate the practical usefulness of our theory by means of numerical experiments, showing how our analysis can significantly impact the performance of DL-ROMs. [ABSTRACT FROM AUTHOR]

Abstract With the advent of big data, it has become increasingly difficult to obtain high-quality data. Solutions are required to remove undesired outlier samples from massively large datasets. Ship operators rely on high-frequency in-service datasets recorded onboard the ships for monitoring the performance of their fleet. The large in-service datasets are known to be highly unbalanced, making it difficult to adopt ordinary outlier detection techniques, as they would also result in the removal of rare but quite valuable data samples. Thus, the current work proposes to establish a correlation-based outlier detection scheme for ships’ in-service datasets using two well-known dimensionality reduction methods, namely, Principal Component Analysis (PCA) and Autoencoders. The correlation-based approach detects samples which do not fit the prominent correlations present in the dataset and avoids misidentifying the rare but correlation-following samples in the sparse regions of data domain. The study also attempts to provide the physical meaning of the latent variables obtained using PCA. The effectiveness of the proposed methodology is proven using an actual dataset recorded onboard a ship.

In-vehicle communication has been optimized day to day to keep updated of the technologies. Control area network (CAN) is used as a standard communication method because of its efficient and reliable connection. However, CAN is prone to several network level attacks because of its lack in security mechanisms. Various methods have been introduced to incorporate this in CAN. We proposed an unsupervised method of intrusion detection for in-vehicle communication networks by combining the optimal feature extracting ability of autoencoders and more precise clustering using fuzzy C-means (FCM). The proposed method is light weight and requires less computation time. We performed an extensive experiment and achieved an accuracy of 75.51 % with the ML350 in-vehicle intrusion dataset. By experimental result, the proposed method also works better for other intrusion detection problems like wireless intrusion detection datasets such as WNS-DS with accuracy of 84.05 % and network intrusion detection datasets such as KDDCup with accuracy 60.63 % , UNSW_NB15 with accuracy 73.62 % and Information Security Center of Excellence (ISCX) with accuracy 74.83 %. Overall, the proposed method outperforms the existing methods and avoids labeled datasets when training an in-vehicle intrusion detection model. The results of the experiment of our proposed method performed on various intrusion detection datasets indicate that the proposed approach is generalized and robust in detecting intrusions and can be effectively deployed in real time to monitor CAN traffic in vehicles and proactively alert during attacks.

Abstract Background Machine learning (ML) classifiers are increasingly used for predicting cardiovascular disease (CVD) and related risk factors using omics data, although these outcomes often exhibit categorical nature and class imbalances. However, little is known about which ML classifier, omics data, or upstream dimension reduction strategy has the strongest influence on prediction quality in such settings. Our study aimed to illustrate and compare different machine learning strategies to predict CVD risk factors under different scenarios. Methods We compared the use of six ML classifiers in predicting CVD risk factors using blood-derived metabolomics, epigenetics and transcriptomics data. Upstream omic dimension reduction was performed using either unsupervised or semi-supervised autoencoders, whose downstream ML classifier performance we compared. CVD risk factors included systolic and diastolic blood pressure measurements and ultrasound-based biomarkers of left ventricular diastolic dysfunction (LVDD; E/e' ratio, E/A ratio, LAVI) collected from 1,249 Finnish participants, of which 80% were used for model fitting. We predicted individuals with low, high or average levels of CVD risk factors, the latter class being the most common. We constructed multi-omic predictions using a meta-learner that weighted single-omic predictions. Model performance comparisons were based on the F1 score. Finally, we investigated whether learned omic representations from pre-trained semi-supervised autoencoders could improve outcome prediction in an external cohort using transfer learning. Results Depending on the ML classifier or omic used, the quality of single-omic predictions varied. Multi-omics predictions outperformed single-omics predictions in most cases, particularly in the prediction of individuals with high or low CVD risk factor levels. Semi-supervised autoencoders improved downstream predictions compared to the use of unsupervised autoencoders. In addition, median gains in Area Under the Curve by transfer learning compared to modelling from scratch ranged from 0.09 to 0.14 and 0.07 to 0.11 units for transcriptomic and metabolomic data, respectively. Conclusions By illustrating the use of different machine learning strategies in different scenarios, our study provides a platform for researchers to evaluate how the choice of omics, ML classifiers, and dimension reduction can influence the quality of CVD risk factor predictions.

The escalating sophistication of malware poses a formidable security challenge, as it evades traditional protective measures. Static analysis, an initial step in malware investigation, involves code scrutiny without actual execution. One static analysis approach employs the conversion of executable files into image representations, harnessing the potency of deep learning models. Convolutional neural networks (CNNs), particularly adept at image classification, have potential for malware detection. However, their inclination towards structured data requires a preprocessing phase to convert software into image-like formats. This paper outlines a methodology for malware detection that involves applying deep learning models to image-converted executable files. Experimental evaluations have been performed by using CNN models, autoencoder-based models, and pre-trained counterparts, all of which have exhibited commendable performance. Consequently, employing deep learning for image-converted executable analysis emerges as a fitting strategy for the static analysis of software. This research is significant because it utilized the largest dataset to date and encompassed a wide range of deep learning models, many of which have not previously been tested together.

Vibration-based fault diagnosis from rotary machinery requires prior feature extraction, feature selection, or dimensionality reduction. Feature extraction is tedious, and computationally expensive. Feature selection presents unique challenges intrinsic to the method adopted. Nonlinear dimensionality reduction may be achieved through kernel transformations, however there is often a trade-off in information to achieve this. Given the above, this study proposes a novel autoencoder (AE) pre-processing framework for vibration-based fault diagnosis in wind turbine (WT) gearboxes. In this study, AEs are used to learn the features of WT gearbox vibration data while simultaneously compressing the data, obviating the need for costly feature engineering and dimensionality reduction. The effectiveness of the proposed framework was evaluated by training genetically optimized linear discriminant analysis (LDA), multilayer perceptron (MLP), and random forest (RF) models, with the AE’s latent space features. The models were evaluated using known classification metrics. The results showed that the performance of the models depends on the size of the AE’s latent space. As the size of the AE’s latent space increased, the quality of features extracted improved until a plateau was observed at a latent space dimension of 10. The AE pre-processed genetically optimized RF, MLP, and LDA models, designated AE-Pre-GO-RF, AE-Pre-GO-MLP, and AE-Pre-GO-LDA, were evaluated for accuracy, sensitivity, and specificity in the classification of seven (7) gearbox fault conditions. The AE-Pre-GO-RF model outperformed its counterparts, scoring 100% for all evaluated metrics, though with the longest training time (239.50 sec). Comparable results were found comparing this study with similar investigations involving traditional vibration processing techniques. More so, it was established that effective fault diagnosis of the WT gearbox can be achieved through manifold learning with AEs without expensive feature engineering. [ABSTRACT FROM AUTHOR]

With the advent of big data, it has become increasingly difficult to obtain high-quality data. Solutions are required to remove undesired outlier samples from massively large datasets. Ship operators rely on high-frequency in-service datasets recorded onboard the ships for monitoring the performance of their fleet. The large in-service datasets are known to be highly unbalanced, making it difficult to adopt ordinary outlier detection techniques, as they would also result in the removal of rare but quite valuable data samples. Thus, the current work proposes to establish a correlation-based outlier detection scheme for ships' in-service datasets using two well-known dimensionality reduction methods, namely, Principal Component Analysis (PCA) and Autoencoders. The correlation-based approach detects samples which do not fit the prominent correlations present in the dataset and avoids misidentifying the rare but correlation-following samples in the sparse regions of data domain. The study also attempts to provide the physical meaning of the latent variables obtained using PCA. The effectiveness of the proposed methodology is proven using an actual dataset recorded onboard a ship. [ABSTRACT FROM AUTHOR]

El Niño Southern Oscillation (ENSO) is the prominent recurrent climatic pattern in the tropical Pacific Ocean with global impacts on regional climates. This study utilizes deep learning to predict the Niño 3.4 index by encoding non-linear sea surface temperature patterns in the tropical Pacific using an autoencoder neural network. The resulting encoded patterns identify crucial centers of action in the Pacific that serve as predictors of the ENSO mode. These patterns are utilized as predictors for forecasting the Niño 3.4 index with a lead time of at least 6 months using the Long Short-Term Memory (LSTM) deep learning model. The analysis uncovers multiple non-linear dipole patterns in the tropical Pacific, with anomalies that are both regionalized and latitudinally oriented that should support a single inter-tropical convergence zone for modeling efforts. Leveraging these encoded patterns as predictors, the LSTM - trained on monthly data from 1950 to 2007 and tested from 2008 to 2022 - shows fidelity in predicting the Niño 3.4 index. The encoded patterns captured the annual cycle of ENSO with a 0.94 correlation between the actual and predicted Niño 3.4 index for lag 12 and 0.91 for lags 6 and 18. Additionally, the 6-month lag predictions excel in detecting extreme ENSO events, achieving an 85% hit rate, outperforming the 70% hit rate at lag 12 and 55% hit rate at lag 18. The prediction accuracy peaks from November to March, with correlations ranging from 0.94 to 0.96. The average correlations in the boreal spring were as large as 0.84, indicating the method has the capability to decrease the spring predictability barrier. [ABSTRACT FROM AUTHOR]

The escalating sophistication of malware poses a formidable security challenge, as it evades traditional protective measures. Static analysis, an initial step in malware investigation, involves code scrutiny without actual execution. One static analysis approach employs the conversion of executable files into image representations, harnessing the potency of deep learning models. Convolutional neural networks (CNNs), particularly adept at image classification, have potential for malware detection. However, their inclination towards structured data requires a preprocessing phase to convert software into image-like formats. This paper outlines a methodology for malware detection that involves applying deep learning models to image-converted executable files. Experimental evaluations have been performed by using CNN models, autoencoder-based models, and pre-trained counterparts, all of which have exhibited commendable performance. Consequently, employing deep learning for imageconverted executable analysis emerges as a fitting strategy for the static analysis of software. This research is significant because it utilized the largest dataset to date and encompassed a wide range of deep learning models, many of which have not previously been tested together. [ABSTRACT FROM AUTHOR]

Identifying unknown types of diseases is a crucial step in preceding retinal imaging classification for the sake of safety, which is known as anomaly detection of retinal imaging. However, the widely-used supervised learning algorithms are not suitable for this problem, since the data of the unknown category is unobtainable. Moreover, for retinal imaging with different types of anomalous regions, using a single-resolution input causes information loss. Therefore, we propose an unsupervised auto-encoder model with multi-resolution inputs and outputs. We provide a theoretical understanding of the effectiveness of reconstruction error and the improvement of self-supervised learning for anomaly detection. Our experiments on two widely-used retinal imaging datasets show that the proposed methods are superior to other methods, and further experiments verify the validity of each part of the proposed method. [ABSTRACT FROM AUTHOR]

In-vehicle communication has been optimized day to day to keep updated of the technologies. Control area network (CAN) is used as a standard communication method because of its efficient and reliable connection. However, CAN is prone to several network level attacks because of its lack in security mechanisms. Various methods have been introduced to incorporate this in CAN. We proposed an unsupervised method of intrusion detection for in-vehicle communication networks by combining the optimal feature extracting ability of autoencoders and more precise clustering using fuzzy C-means (FCM). The proposed method is light weight and requires less computation time. We performed an extensive experiment and achieved an accuracy of 75.51 % with the ML350 in-vehicle intrusion dataset. By experimental result, the proposed method also works better for other intrusion detection problems like wireless intrusion detection datasets such as WNS-DS with accuracy of 84.05 % and network intrusion detection datasets such as KDDCup with accuracy 60.63 %, UNSW_NB15 with accuracy 73.62 % and Information Security Center of Excellence (ISCX) with accuracy 74.83 %. Overall, the proposed method outperforms the existing methods and avoids labeled datasets when training an in-vehicle intrusion detection model. The results of the experiment of our proposed method performed on various intrusion detection datasets indicate that the proposed approach is generalized and robust in detecting intrusions and can be effectively deployed in real time to monitor CAN traffic in vehicles and proactively alert during attacks. [ABSTRACT FROM AUTHOR]

Many initial movements require subsequent corrective movements, but how the motor cortex transitions to make corrections and how similar the encoding is to initial movements is unclear. In our study, we explored how the brain's motor cortex signals both initial and corrective movements during a precision reaching task. We recorded a large population of neurons from two male rhesus macaques across multiple sessions to examine the neural firing rates during not only initial movements but also subsequent corrective movements. AutoLFADS, an autoencoder-based deep-learning model, was applied to provide a clearer picture of neurons' activity on individual corrective movements across sessions. Decoding of reach velocity generalized poorly from initial to corrective submovements. Unlike initial movements, it was challenging to predict the velocity of corrective movements using traditional linear methods in a single, global neural space. We identified several locations in the neural space where corrective submovements originated after the initial reaches, signifying firing rates different than the baseline before initial movements. To improve corrective movement decoding, we demonstrate that a state-dependent decoder incorporating the population firing rates at the initiation of correction improved performance, highlighting the diverse neural features of corrective movements. In summary, we show neural differences between initial and corrective submovements and how the neural activity encodes specific combinations of velocity and position. These findings are inconsistent with assumptions that neural correlations with kinematic features are global and independent, emphasizing that traditional methods often fall short in describing these diverse neural processes for online corrective movements. [ABSTRACT FROM AUTHOR]