Linear Discriminant Analysis Classifier Research Articles

Leveraging machine learning for predicting acute graft-versus-host disease grades in allogeneic hematopoietic cell transplantation for T-cell prolymphocytic leukaemia

Orphan diseases, exemplified by T-cell prolymphocytic leukemia, present inherent challenges due to limited data availability and complexities in effective care. This study delves into harnessing the potential of machine learning to enhance care strategies for orphan diseases, specifically focusing on allogeneic hematopoietic cell transplantation (allo-HCT) in T-cell prolymphocytic leukemia. The investigation evaluates how varying numbers of variables impact model performance, considering the rarity of the disease. Utilizing data from the Center for International Blood and Marrow Transplant Research, the study scrutinizes outcomes following allo-HCT for T-cell prolymphocytic leukemia. Diverse machine learning models were developed to forecast acute graft-versus-host disease (aGvHD) occurrence and its distinct grades post-allo-HCT. Assessment of model performance relied on balanced accuracy, F1 score, and ROC AUC metrics. The findings highlight the Linear Discriminant Analysis (LDA) classifier achieving the highest testing balanced accuracy of 0.58 in predicting aGvHD. However, challenges arose in its performance during multi-class classification tasks. While affirming the potential of machine learning in enhancing care for orphan diseases, the study underscores the impact of limited data and disease rarity on model performance.

A New Sub-Class Linear Discriminant for Miniature Spectrometer Based Food Analysis

The well-known and extensively studied Linear Discriminant Analysis (LDA) can have its performance lowered in scenarios where data is not homoscedastic or not Gaussian. That is, the classical assumptions when LDA models are built are not applicable, and consequently LDA projections would not be able to extract the needed features to explain the intrinsic structure of data and for classes to be separated. As with many real word data sets, data obtained using miniature spectrometers can suffer from such drawbacks which would limit the deployment of such technology needed for food analysis. The solution presented in the paper is to divide classes into subclasses and to use means of sub classes, classes, and data in the suggested between classes scatter metric. Further, samples belonging to the same subclass are used to build a measure of within subclass scatterness. Such a solution solves the shortcoming of the classical LDA. The obtained results when using the proposed solution on food data and on general machine learning datasets show that the work in this paper compares well to and is very competitive with similar sub-class LDA algorithms in the literature. An extension to a Hilbert space is also presented; and the kernel version of the presented solution can be fused with its linear counter parts to yield improved classification rates.

Bacterial Disease Detection of Cherry Plant Using Deep Features

Although the cherry plant is widely grown in the world and Turkey, it is a fruit tree that is difficult to grow and maintain. It can be exposed to various pesticide diseases, especially during fruiting. Today, approaches based on expert reviews and analyses are used for the identification of these diseases. In addition, cherry producers are trying to detect diseases with their knowledge based on experience. Computer-aided agricultural analysis systems are also being developed depending on the rapid developments in technology. These systems help to monitor all processes from planting, cultivation, and harvesting of agricultural products and to make decisions to grow the products healthily. One of the most important issues to be detected and monitored with these systems is plant diseases. The features of the cherry plant disease will be determined by using a pre-trained convolutional neural network (CNN) model which is DarkNet-19, within the scope of this study. These machine learning-based features have been used for the detection of bacteria-based diseases commonly seen on the leaves of cherry plants. The acquired features are classified with Linear Discriminant Analysis, K-Nearest Neighbor, and Support Vector Machine classifiers to solve the multi-class problem including diseased (less and very) and healthy plants. The experimental results show that a success rate of 88.1% was obtained in the detection of the disease.

Effect of Sample Presentation on the Classification of Black Soldier Fly Larvae Using Near-Infrared Spectroscopy

Black soldier fly larvae (BSFL) (Hermetia illucens) reared on food waste streams are considered a sustainable source of protein in feed livestock diets. Recently, portable near-infrared spectroscopy (NIR) instruments have been assessed to monitor the consistency and quality of food waste streams used to feed black soldier fly larvae. During the application of NIR spectroscopy, sample presentation (e.g., drying, processing, particle size) plays an important role in the accuracy of the models developed (quantitative or qualitative analysis). The objective of this study was to evaluate the effect of sample presentation (number of larvae used during the scanning of BSFL) on the accuracy of classification models developed to trace the food waste stream (e.g., supermarket of childcare) used to feed the larvae. BSFL samples were sourced from two waste streams and scanned as half, 1, 2, or 3 larvae using an NIR portable instrument (MicroNIR, Viavi, Milpitas, California, USA). Principal component analysis (PCA) and linear discriminant analysis (LDA) were used to analyze the NIR data and to classify the samples according to the waste stream. The main differences in the NIR spectra of the BSFL samples associated with the number of larvae scanned were observed around 1200 nm, mainly associated with the C-H overtones (lipids). The classification results showed that high classification rates (>93%) were obtained regardless of the number of larvae scanned, ranging from 93% (using 0.5 larvae) to 100% (using 1, 2, or 3 larvae samples). Overall, the number of larvae scanned had minimal to no effect on the accuracy of the LDA classification models. The present study demonstrated that a portable NIR instrument can be suitable for an initial rapid classification or determination of the origin of the waste stream used to feed the BSFL.

Feature Importance Analysis and Machine Learning for Alzheimer's Disease Early Detection: Feature Fusion of the Hippocampus, Entorhinal Cortex, and Standardized Uptake Value Ratio.

Alzheimer's disease (AD) is a progressive neurological disorder characterized by mild memory loss and ranks as a leading cause of mortality in the USA, accounting for approximately 120,000 deaths per year. It is also the primary form of dementia. Early detection is critical for timely intervention as the neurodegenerative process often starts 15-20 years before cognitive symptoms manifest. This study focuses on determining feature importance in AD classification using fused texture features from 3D magnetic resonance imaging hippocampal and entorhinal cortex and standardized uptake value ratio (SUVR) derived from positron emission tomography (PET) images. To achieve this objective, we employed four distinct classifiers (Linear Support Vector Classification, Linear Discriminant Analysis, Logistic Regression, and Logistic Regression Classifier with Stochastic Gradient Descent Learning). These classifiers were used to derive both average and top-ranked importance scores for each feature based on their outputs. Our framework is designed to distinguish between two classes, AD-negative (or mild cognitive impairment stable [MCIs]) and AD-positive (or MCI conversion [MCIc]), using a probabilistic neural network classifier and the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The findings from the feature importance highlight the crucial role of the GLCM texture features extracted from the hippocampus and entorhinal cortex, demonstrating their superior performance compared to the volume and SUVR. GLCM texture AD classification achieved approximately 90% sensitivity in identifying MCIc cases while maintaining low false positives (below 30%) when fused with other features. Moreover, the receiver operating characteristic curves validate the GLCMs' superior performance in distinguishing between MCIs and MCIc. Additionally, fusing different types of features improved classification performance compared to relying solely on any single feature category. Our study emphasizes the pivotal role of GLCM texture features in early Alzheimer's detection.

Analyzing lower body movements using machine learning to classify autistic children

Autism spectrum disorder is a neurological disorder that affects children at an early age and its symptoms appear in varying degrees. Early detection of ASD and follow-up of treatment by specialists help improve autistic people's lives and reduce the symptoms they suffer from. In the past few years, a group of studies conducted gait analysis to diagnose children with autism, and although the results of these studies showed weak motor skills of Autism Spectrum Disorder children (ASD) compared to their peers of Typically Developing children (TD), there are some challenges facing researchers in this field. The first is the ability to create A safe, effective, friendly environment that reduces tension in ASD children and helps classify children into ASD/TD effectively. And the second is the ability to create an automated ASD diagnosis system. In this work, a system based on machine learning and augmented reality technology has been proposed to create an effective and friendly interactive environment that helps diagnose ASD and classify children to ASD / TD. The movement of the lower limbs of 15 ASD children and 15 TD children are tracked via a marker-less technique through a Kinect v2 sensor when playing a specific game based on kicking the ball task, that is using augmented reality technology. Then the kinematics features are extracted through Linear Discriminant Analysis technology. To determine these features' ability in the classification process, three machine learning algorithms are used, namely Support Vector Machine, Linear Discriminant Analysis, and Decision Tree. The results showed that the obtained kinematics features can classify children into ASD/TD, where the Support Vector Machine classifier obtained a high accuracy of 96.7% with sensitivity equal to 93.3% and specificity equal to 100%. In addition, the Linear Discriminant Analysis classifier obtained less accuracy of 93.3% with sensitivity equal to 93.3% and specificity equal to 93.3% compared with the Support Vector Machine classifier. Where the Decision Tree classifier obtained the lowest accuracy of 80.0% with sensitivity equal to 73.3% and specificity equal to 86.7% compared with the Support Vector Machine and Linear Discriminant Analysis classifiers. In addition to that, when using Linear Discriminant Analysis to reduce dimensions and extract features, the accuracy, sensitivity, and specificity of the Support Vector Machine classifier were increased and achieved by 100%. Based on these results, it has been proven that the proposed method is effective in classifying children to ASD/TD.

On the Equivalence of Linear Discriminant Analysis and Least Squares Regression.

Studying the relationship between linear discriminant analysis (LDA) and least squares regression (LSR) is of great theoretical and practical significance. It is well-known that the two-class LDA is equivalent to an LSR problem, and directly casting multiclass LDA as an LSR problem, however, becomes more challenging. Recent study reveals that the equivalence between multiclass LDA and LSR can be established based on a special class indicator matrix, but under a mild condition which may not hold under the scenarios with low-dimensional or oversampled data. In this article, we show that the equivalence between multiclass LDA and LSR can be established based on arbitrary linearly independent class indicator vectors and without any condition. In addition, we show that LDA is also equivalent to a constrained LSR based on the data-dependent indicator vectors. It can be concluded that under exactly the same mild condition, such two regressions are both equivalent to the null space LDA method. Illuminated by the equivalence of LDA and LSR, we propose a direct LDA classifier to replace the conventional framework of LDA plus extra classifier. Extensive experiments well validate the above theoretic analysis.

A compact Fourier-transform near-infrared spectrophotometer and chemometrics for characterizing a comprehensive set of seized ecstasy samples

A comprehensive data set of ecstasy samples containing MDMA (N-methyl-3,4-methylenedioxyamphetamine) and MDA (3,4-methylenedioxyamphetamine) seized by the Brazilian Federal Police was characterized using spectral data obtained by a compact, low-cost, near-infrared Fourier-transform based spectrophotometer. Qualitative and quantitative characterization was accomplished using soft independent modeling of class analogy (SIMCA), linear discriminant analysis (LDA) classification, discriminating partial least square (PLS-DA), and regression models based on partial least square (PLS). By applying chemometric analysis, a protocol can be proposed for the in-field screening of seized ecstasy samples. The validation led to an efficiency superior to 96 % for ecstasy classification and estimating total actives, MDMA, and MDA content in the samples with a root mean square error of validation of 4.4, 4.2, and 2.7 % (m/m), respectively. The feasibility and drawbacks of the NIR technology applied to ecstasy characterization and the compromise between false positives and false negatives rate achieved by the classification models are discussed and a new approach to improve the classification robustness was proposed considering the forensic context.

Exploring EEG-based motor imagery decoding: a dual approach using spatial features and spectro-spatial Deep Learning model IFNet.

In recent years, the decoding of motor imagery (MI) from electroencephalography (EEG) signals has become a focus of research for brain-machine interfaces (BMIs) and neurorehabilitation. However, EEG signals present challenges due to their non-stationarity and the substantial presence of noise commonly found in recordings, making it difficult to design highly effective decoding algorithms. These algorithms are vital for controlling devices in neurorehabilitation tasks, as they activate the patient's motor cortex and contribute to their recovery. This study proposes a novel approach for decoding MI during pedalling tasks using EEG signals. A widespread approach is based on feature extraction using Common Spatial Patterns (CSP) followed by a linear discriminant analysis (LDA) as a classifier. The first approach covered in this work aims to investigate the efficacy of a task-discriminative feature extraction method based on CSP filter and LDA classifier. Additionally, the second alternative hypothesis explores the potential of a spectro-spatial Convolutional Neural Network (CNN) to further enhance the performance of the first approach. The proposed CNN architecture combines a preprocessing pipeline based on filter banks in the frequency domain with a convolutional neural network for spectro-temporal and spectro-spatial feature extraction. To evaluate the approaches and their advantages and disadvantages, EEG data has been recorded from several able-bodied users while pedalling in a cycle ergometer in order to train motor imagery decoding models. The results show levels of accuracy up to 80% in some cases. The CNN approach shows greater accuracy despite higher instability.

Ligand and structure-based discovery of phosphorus-containing compounds as potential metalloproteinase inhibitors

ABSTRACT In this study, a methodology is proposed, combining ligand- and structure-based virtual screening tools, for the identification of phosphorus-containing compounds as inhibitors of zinc metalloproteases. First, we use Dragon molecular descriptors to develop a Linear Discriminant Analysis classification model, which is widely validated according to the OECD principles. This model is simple, robust, stable and has good discriminating power. Furthermore, it has a defined applicability domain and it is used for virtual screening of the DrugBank database. Second, docking experiments are carried out on the identified compounds that showed good binding energies to the enzyme thermolysin. Considering the potential toxicity of phosphorus-containing compounds, their toxicological profile is evaluated according to Protox II. Of the five molecules evaluated, two show carcinogenic and mutagenic potential at small LD50, not recommended as drugs, while three of them are classified as non-toxic, and could constitute a starting point for the development of new vasoactive metalloprotease inhibitor drugs. According to molecular dynamics simulation, two of them show stable interactions with the active site maintaining coordination with the metal. A high agreement is evident between QSAR, docking and molecular dynamics results, demonstrating the potentialities of the combination of these tools.

Adaptive LDA Classifier Enhances Real-Time Control of an EEG Brain-Computer Interface for Decoding Imagined Syllables.

Brain-Computer Interfaces (BCIs) aim to establish a pathway between the brain and an external device without the involvement of the motor system, relying exclusively on neural signals. Such systems have the potential to provide a means of communication for patients who have lost the ability to speak due to a neurological disorder. Traditional methodologies for decoding imagined speech directly from brain signals often deploy static classifiers, that is, decoders that are computed once at the beginning of the experiment and remain unchanged throughout the BCI use. However, this approach might be inadequate to effectively handle the non-stationary nature of electroencephalography (EEG) signals and the learning that accompanies BCI use, as parameters are expected to change, and all the more in a real-time setting. To address this limitation, we developed an adaptive classifier that updates its parameters based on the incoming data in real time. We first identified optimal parameters (the update coefficient, UC) to be used in an adaptive Linear Discriminant Analysis (LDA) classifier, using a previously recorded EEG dataset, acquired while healthy participants controlled a binary BCI based on imagined syllable decoding. We subsequently tested the effectiveness of this optimization in a real-time BCI control setting. Twenty healthy participants performed two BCI control sessions based on the imagery of two syllables, using a static LDA and an adaptive LDA classifier, in randomized order. As hypothesized, the adaptive classifier led to better performances than the static one in this real-time BCI control task. Furthermore, the optimal parameters for the adaptive classifier were closely aligned in both datasets, acquired using the same syllable imagery task. These findings highlight the effectiveness and reliability of adaptive LDA classifiers for real-time imagined speech decoding. Such an improvement can shorten the training time and favor the development of multi-class BCIs, representing a clear interest for non-invasive systems notably characterized by low decoding accuracies.

Geometrical Interpretation and Design of Multilayer Perceptrons.

The multilayer perceptron (MLP) neural network is interpreted from the geometrical viewpoint in this work, that is, an MLP partition an input feature space into multiple nonoverlapping subspaces using a set of hyperplanes, where the great majority of samples in a subspace belongs to one object class. Based on this high-level idea, we propose a three-layer feedforward MLP (FF-MLP) architecture for its implementation. In the first layer, the input feature space is split into multiple subspaces by a set of partitioning hyperplanes and rectified linear unit (ReLU) activation, which is implemented by the classical two-class linear discriminant analysis (LDA). In the second layer, each neuron activates one of the subspaces formed by the partitioning hyperplanes with specially designed weights. In the third layer, all subspaces of the same class are connected to an output node that represents the object class. The proposed design determines all MLP parameters in a feedforward one-pass fashion analytically without backpropagation. Experiments are conducted to compare the performance of the traditional backpropagation-based MLP (BP-MLP) and the new FF-MLP. It is observed that the FF-MLP outperforms the BP-MLP in terms of design time, training time, and classification performance in several benchmarking datasets. Our source code is available at https://colab.research.google.com/drive/1Gz0L8AnT4ijrUchrhEXXsnaacrFdenn?usp = sharing.

Storm Surges and Sea Level Rise Cluster Hydrological Variables Across a Coastal Forest Bordering a Salt Marsh

AbstractSea level rise and storm surges drive coastal forest retreat and salt marsh expansion. Both salinization and flooding control ecological zonation and ecosystem transition in coastal areas. Hydrological variables, if coupled with ecological surveys, can explain the different stages of coastal forest retreat and marsh encroachment. In this research, long‐term data of a host of hydrological variables collected along transects from marsh to inner forest were analyzed. Linear discriminant analysis (LDA) was used to identify the primary hydrological variables responsible for the forest‐marsh gradient and their seasonal patterns. Water content (WC) in the soil (WC) and groundwater electrical conductivity (EC) were found to be the main variables responsible for the hydrological differences among the sites. Higher values of WC and EC were found in the low‐forest area near the salt marsh, with hydrological differences between forest levels reflected in ecological community structure. In particular, some sites were characterized by high EC while others by high WC values, suggesting significant spatial variations within hundreds of meters. The forested area, relatively flat in elevation, was characterized by limited hydraulic gradients and consequently lateral discharges. These characteristics made the role of groundwater level negligible in driving the hydrological clustering. Seasonal LDA data suggest that the sites are hydrologically different during winter (higher distance among clusters of variables) and similar during summer (low distance among clusters). In the study area, higher rainfall occurs during summer, decreasing groundwater EC in areas characterized by low canopy cover (dying forest). Rainfall moved low forest sites closer to the pristine high forest in the LDA analysis. During storm surge events, the distance between clusters decreased, indicating uniform salinization and flooding across the forest. Therefore, we conclude that ecological zonation in a coastal forest is reflected in seasonal hydrological differences in the absence of storm surges. Storm surges do not produce contrasting hydrological conditions and might not be responsible for ecological differences in the short‐term. On the contrary, differences in hydrological recovery are responsible for forest zonation. An additional analysis carried out using a binary Marsh‐Healthy forest LDA classifier indicates when each site switches from a forest hydrological state to a salt‐marsh hydrological state. Our results are useful for long‐term predictions of the ecological evolution of the forest–salt marsh ecotone.

Reflectance spectra for identifying stress in different parts of leaf: a case study on oil palm seedlings

ABSTRACT In this study, the spectral responses to drought stress of different parts in the leaf of oil palm seedlings named base, middle, and tip were investigated. The ability to detect stress even before symptoms emerge requires knowledge of which part of oil palm leaves responds more quickly to the stress. The analysis of the reflectance spectra in region 650–1050 nm was conducted on respective sections of the leaves of the oil palm seedlings. The analysis revealed that the stress affects the tip of the leaf, followed by the middle and then the base. It was noticed that the greatest loss of water and chlorophyll content was at the tip of the leaf. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) were used for clustering, while support vector machine (SVM) and linear discriminant analysis (LDA) were applied for categorization purposes. The outcomes of the PCA and HCA showed that the separation between the samples was based on the day and stress levels at respective sections of the leaf. With this, the possession of distinct morphological and physiological features by each part of the leaf can be concluded. From the PCA loadings, it was found that the regions 699–756 nm, 833–877 nm, and 933–958 nm showed noticeable bands and can be used to distinguish between the oil palm seedlings under stress. In addition, LDA and SVM classifiers demonstrated that the prediction accuracy of the stress level in oil palm seedlings was not influenced by the location in the leaf where the spectra were acquired.

Analysing the behaviour change of brain regions of methamphetamine abusers using electroencephalogram signals: Hope to design a decision support system.

Long-term use of methamphetamine (meth) causes cognitive and neuropsychological impairments. Analysing the impact of this substance on the human brain can aid prevention and treatment efforts. In this study, the electroencephalogram (EEG) signals of meth abusers in the abstinence period and healthy subjects were recorded during eyes-closed and eyes-opened states to distinguish the brain regions that meth can significantly influence. In addition, a decision support system (DSS) was introduced as a complementary method to recognize substance users accompanied by biochemical tests. According to these goals, the recorded EEG signals were pre-processed and decomposed into frequency bands using the discrete wavelet transform (DWT) method. For each frequency band, energy, KS entropy, Higuchi and Katz fractal dimensions of signals were calculated. Then, statistical analysis was applied to select features whose channels contain a p-value less than 0.05. These features between two groups were compared, and the location of channels containing more features was specified as discriminative brain areas. Due to evaluating the performance of features and distinguishing the two groups in each frequency band, features were fed into a k-nearest neighbour (KNN), support vector machine (SVM), multilayer perceptron neural networks (MLP) and linear discriminant analysis (LDA) classifiers. The results indicated that prolonged consumption of meth has a considerable impact on the brain areas responsible for working memory, motor function, attention, visual interpretation, and speech processing. Furthermore, the best classification accuracy, almost 95.8%, was attained in the gamma band during the eyes-closed state.

Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments

Coughing, a prevalent symptom of many illnesses, including COVID-19, has led researchers to explore the potential of cough sound signals for cost-effective disease diagnosis. Traditional diagnostic methods, which can be expensive and require specialized personnel, contrast with the more accessible smartphone analysis of coughs. Typically, coughs are classified as wet or dry based on their phase duration. However, the utilization of acoustic analysis for diagnostic purposes is not widespread. Our study examined cough sounds from 1183 COVID-19-positive patients and compared them with 341 non-COVID-19 cough samples, as well as analyzing distinctions between pneumonia and asthma-related coughs. After rigorous optimization across frequency ranges, specific frequency bands were found to correlate with each respiratory ailment. Statistical separability tests validated these findings, and machine learning algorithms, including linear discriminant analysis and k-nearest neighbors classifiers, were employed to confirm the presence of distinct frequency bands in the cough signal power spectrum associated with particular diseases. The identification of these acoustic signatures in cough sounds holds the potential to transform the classification and diagnosis of respiratory diseases, offering an affordable and widely accessible healthcare tool.

Feature extraction and classification of different hand movements from the emg signal using linear discriminant analysis classifier

In biomedical research, Electromyography (EMG) data play a crucial role as a bridge between human motions and machine interpretation, offering valuable insights into muscle activation. EMG signals give vital information on hand movements in the context of applications like gesture recognition, prosthetic control, and rehabilitation. This paper describes the classification of EMG signals based on muscle motions, which makes it simpler to identify distinct gestures or movements. A Linear Discriminant Analysis (LDA) classifier is used to differentiate between various classes of muscle activity. In order to record EMG signals during hand motions, surface electrodes are carefully positioned on pertinent muscles. Muscle activity may be tracked in real time with these non-invasive electrodes. In order to extract meaningful information from these signals, which are complex and frequently contaminated by noise, strong feature extraction techniques are needed. When working with noisy signals, denoising is a commonly used approach to restoring the original quality of the source data. It attempts to maintain relevant information by reducing noise in the raw EMG signals. In order to retrieve only the pertinent information from the original EMG signal data, any unnecessary noise must first be removed. Through the identification of key characteristics in the time, frequency, and time-frequency domains, it transforms unstructured EMG data. This procedure improves the next step of classification, which is the identification and classification of patterns in the EMG signals. Ultimately, the obtained information is employed to classify signals by the Linear Discriminant Analysis (LDA) classifier, demonstrating a distinction between various muscle motions with over 80% accuracy.

Designing a motion-onset visual evoked potential-based brain-computer interface to control a computer game

Brain-computer interface (BCI) establishes an alternative direct communication channel between the brain and computer or other external devices. Motion-onset visual evoked potential (mVEP) related to the individual perception of movement is among synchronous BCI system that utilizes external stimulus. mVEPs stimulation paradigm is like an oddball stimulation paradigm. Researchers have recently been investigating mVEPs to control a computer game. To control a computer game, they used translation stimulus to evoke these potentials in EEG brain signals. In this study, we examine designing a computer game with four different types of stimuli, including translation, contraction, expansion, and rotation. We also used time-domain and wavelet coefficients for the feature extraction. Also, we used different types of linear discriminant analysis (LDA) classification methods, including least absolute shrinkage and selection operator (LASSO), stepwise LDA (SWLDA); moreover, and spatial-temporal discriminant analysis (STDA) for detecting the target stimulus. Our results demonstrate that contraction, expansion, and rotation stimuli, as well as translation, could be employed to control a BCI game. Our results showed that subjects got higher scores, game accuracy control, and information transfer rate using the rotation stimulus with SWLDA/STDA classification methods.

An Efficient Greedy Search Algorithm for High-dimensional Linear Discriminant Analysis.

High-dimensional classification is an important statistical problem that has applications in many areas. One widely used classifier is the Linear Discriminant Analysis (LDA). In recent years, many regularized LDA classifiers have been proposed to solve the problem of high-dimensional classification. However, these methods rely on inverting a large matrix or solving large-scale optimization problems to render classification rules-methods that are computationally prohibitive when the dimension is ultra-high. With the emergence of big data, it is increasingly important to develop more efficient algorithms to solve the high-dimensional LDA problem. In this paper, we propose an efficient greedy search algorithm that depends solely on closed-form formulae to learn a high-dimensional LDA rule. We establish theoretical guarantee of its statistical properties in terms of variable selection and error rate consistency; in addition, we provide an explicit interpretation of the extra information brought by an additional feature in a LDA problem under some mild distributional assumptions. We demonstrate that this new algorithm drastically improves computational speed compared with other high-dimensional LDA methods, while maintaining comparable or even better classification performance.

Multimodality radiomics prediction of radiotherapy-induced the early proctitis and cystitis in rectal cancer patients: a machine learning study

Purpose. This study aims to predict radiotherapy-induced rectal and bladder toxicity using computed tomography (CT) and magnetic resonance imaging (MRI) radiomics features in combination with clinical and dosimetric features in rectal cancer patients. Methods. A total of sixty-three patients with locally advanced rectal cancer who underwent three-dimensional conformal radiation therapy (3D-CRT) were included in this study. Radiomics features were extracted from the rectum and bladder walls in pretreatment CT and MR-T2W-weighted images. Feature selection was performed using various methods, including Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-square (Chi2), Analysis of Variance (ANOVA), Recursive Feature Elimination (RFE), and SelectPercentile. Predictive modeling was carried out using machine learning algorithms, such as K-nearest neighbor (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Gradient Boosting (XGB), and Linear Discriminant Analysis (LDA). The impact of the Laplacian of Gaussian (LoG) filter was investigated with sigma values ranging from 0.5 to 2. Model performance was evaluated in terms of the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, and specificity. Results. A total of 479 radiomics features were extracted, and 59 features were selected. The pre-MRI T2W model exhibited the highest predictive performance with an AUC: 91.0/96.57%, accuracy: 90.38/96.92%, precision: 90.0/97.14%, sensitivity: 93.33/96.50%, and specificity: 88.09/97.14%. These results were achieved with both original image and LoG filter (sigma = 0.5–1.5) based on LDA/DT-RF classifiers for proctitis and cystitis, respectively. Furthermore, for the CT data, AUC: 90.71/96.0%, accuracy: 90.0/96.92%, precision: 88.14/97.14%, sensitivity: 93.0/96.0%, and specificity: 88.09/97.14% were acquired. The highest values were achieved using XGB/DT-XGB classifiers for proctitis and cystitis with LoG filter (sigma = 2)/LoG filter (sigma = 0.5–2), respectively. MRMR/RFE-Chi2 feature selection methods demonstrated the best performance for proctitis and cystitis in the pre-MRI T2W model. MRMR/MRMR-Lasso yielded the highest model performance for CT. Conclusion. Radiomics features extracted from pretreatment CT and MR images can effectively predict radiation-induced proctitis and cystitis. The study found that LDA, DT, RF, and XGB classifiers, combined with MRMR, RFE, Chi2, and Lasso feature selection algorithms, along with the LoG filter, offer strong predictive performance. With the inclusion of a larger training dataset, these models can be valuable tools for personalized radiotherapy decision-making.