This paper introduces two novel approaches for Online Multi-Task Learning (MTL) Regression Problems. We employ a high performance graph-based MTL formulation and develop its recursive versions based on the Weighted Recursive Least Squares (WRLS) and the Online Sparse Least Squares Support Vector Regression (OSLSSVR). Adopting task-stacking transformations, we demonstrate the existence of a single matrix incorporating the relationship of multiple tasks and providing structural information to be embodied by the MT-WRLS method in its initialization procedure and by the MT-OSLSSVR in its multi-task kernel function. Contrasting the existing literature, which is mostly based on Online Gradient Descent (OGD) or cubic inexact approaches, we achieve exact and approximate recursions with quadratic per-instance cost on the dimension of the input space (MT-WRLS) or on the size of the dictionary of instances (MT-OSLSSVR). We compare our online MTL methods to other contenders in a real-world wind speed forecasting case study, evidencing the significant gain in performance of both proposed approaches.

One-class classification (OCC) is the problem of deciding whether an observed sample belongs to a target class. We consider the problem of learning an OCC model that performs as the generalized likelihood ratio test (GLRT), given a dataset containing samples of the target class. The GLRT solves the same problem when the statistics of the target class are available. The GLRT is a well-known and provably optimal (under specific assumptions) classifier. To this end, we consider both the multilayer perceptron neural network (NN) and the support vector machine (SVM) models. They are trained as two-class classifiers using an artificial dataset for the alternative class, obtained by generating random samples, uniformly over the domain of the target-class dataset. We prove that, under suitable assumptions, the models converge (with a large dataset) to the GLRT. Moreover, we show that the one-class least squares SVM (OCLSSVM) with suitable kernels at convergence performs as the GLRT. Lastly, we prove that the widely used autoencoder (AE) classifier does not generally provide the GLRT.

The free electron laser(FEL) at Stanford Linear Accelerator Center(SLAC) is an ultra-fast X-ray laser. As one of the most advanced X-ray light source [5] [6], it is famous for its high brightness and short pulse duration: it is 10 billion times brighter than the world's second brightest light source; the pulse duration is several tens femtoseconds.It plays a pivotal role in both fundamental science research and applied research [6]. The mechanism behind this laser is very delicate [5]. Thus to keep the laser in optimal working condition is challenging.The positions of the electron beams and the laser beams are of fundamental importance in the control and maintenance of this FEL. Currently, the task of locating beam spots heavily depends on human labor. This is mainly attributed to the wide varieties of beam spots and the presentation of strong noises as demonstrated in Figure 1, where the white square marks the boundary of the beam spot. Each picture requires a long sequence of signal processing methods to mark the beam position.

The complexity of high-dimensional datasets presents significant challenges for machine learning models, including overfitting, computational complexity, and difficulties in interpreting results. To address these challenges, it is essential to identify an informative subset of features that captures the essential structure of the data. In this study, the authors propose Multi-view Sparse Laplacian Eigenmaps (MSLE) for feature selection, which effectively combines multiple views of the data, enforces sparsity constraints, and employs a scalable optimization algorithm to identify a subset of features that capture the fundamental data structure. MSLE is a graph-based approach that leverages multiple views of the data to construct a more robust and informative representation of high-dimensional data. The method applies sparse eigendecomposition to reduce the dimensionality of the data, yielding a reduced feature set. The optimization problem is solved using an iterative algorithm alternating between updating the sparse coefficients and the Laplacian graph matrix. The sparse coefficients are updated using a soft-thresholding operator, while the graph Laplacian matrix is updated using the normalized graph Laplacian. To evaluate the performance of the MSLE technique, the authors conducted experiments on the UCI-HAR dataset, which comprises 561 features, and reduced the feature space by 10 to 90%. Our results demonstrate that even after reducing the feature space by 90%, the Support Vector Machine (SVM) maintains an error rate of 2.72%. Moreover, the authors observe that the SVM exhibits an accuracy of 96.69% with an 80% reduction in the overall feature space.

Quantum Kernel Estimation (QKE) is a technique based on leveraging a quantum computer to estimate a kernel function that is classically difficult to calculate, which is then used by a classical computer for training a Support Vector Machine (SVM). Given the high number of 2-local operators necessary for realizing a feature mapping hard to simulate classically, a high qubit connectivity is needed, which is not currently possible on superconducting devices. For this reason, neutral atom quantum computers can be used, since they allow to arrange the atoms with more freedom. Examples of neutral-atom-based QKE can be found in the literature, but they are focused on graph learning and use the analogue approach. In this paper, a general method based on the gate model is presented. After deriving 1-qubit and 2-qubit gates starting from laser pulses, a parameterized sequence for feature mapping on 3 qubits is realized. This sequence is then used to empirically compute the kernel matrix starting from a dataset, which is finally used to train the SVM. It is also shown that this process can be generalized up to N qubits taking advantage of the more flexible arrangement of atoms that this technology allows. The accuracy is shown to be high despite the small dataset and the low separation. This is the first paper that not only proposes an algorithm for explicitly deriving a universal set of gates but also presents a method of estimating quantum kernels on neutral atom devices for general problems using the gate model.

Accurately detecting and predicting lane change (LC)processes can help autonomous vehicles better understand their surrounding environment, recognize potential safety hazards, and improve traffic safety. This paper focuses on LC processes and compares different machine learning methods' performance to recognize LC intention from high-dimensionality time series data. To validate the performance of the proposed models, a total number of 1023 vehicle trajectories is extracted from the CitySim dataset. For LC intention recognition issues, the results indicate that with ninety-eight percent of classification accuracy, ensemble methods reduce the impact of Type II and Type III classification errors. Without sacrificing recognition accuracy, the LightGBM demonstrates a sixfold improvement in model training efficiency than the XGBoost algorithm.

This paper compares and explores the performance of both mobile device camera and laptop camera as convenient tool for capturing images for non-invasive detection of Diabetes Mellitus (DM) using facial block texture features. Participants within age bracket 20 to 79 years old were chosen for the dataset. 12mp and 7mp mobile cameras, and a laptop camera were used to take the photo under normal lighting condition. Extracted facial blocks were classified using k-Nearest Neighbors (k-NN) and Support Vector Machine (SVM). 100 images were captured, preprocessed, filtered using Gabor, and iterated. Performance of the system was measured in terms of accuracy, specificity, and sensitivity. Best performance of 96.7% accuracy, 100% sensitivity, and 93% specificity were achieved from 12mp back camera using SVM with 100 images.

The topic of Climate Change (CC) has received limited attention in NLP despite its urgency. Activists and policymakers need NLP tools to effectively process the vast and rapidly growing unstructured textual climate reports into structured form. To tackle this challenge we introduce two new large-scale climate questionnaire datasets and use their existing structure to train self-supervised models. We conduct experiments to show that these models can learn to generalize to climate disclosures of different organizations types than seen during training. We then use these models to help align texts from unstructured climate documents to the semi-structured questionnaires in a human pilot study. Finally, to support further NLP research in the climate domain we introduce a benchmark of existing climate text classification datasets to better evaluate and compare existing models.

The hydrometallurgical method of zinc production involves leaching zinc from ore and then separating the solid residue from the liquid solution by pressure filtration. This separation process is very important since the solid residue contains some moisture that can reduce the amount of zinc recovered. This study modeled the pressure filtration process through Random Forest (RF) and Support Vector Machine (SVM). The models take continuous variables (extracted features) from the lab samples as inputs. Thus, regression models namely Random Forest Regression (RFR) and Support Vector Regression (SVR) were chosen. A total dataset was obtained during the pressure filtration process in two conditions: 1) Polypropylene (S1) and 2) Polyester fabrics (S2). To predict the cake moisture, solids concentration (0.2 and 0.38), temperature (35 and 65 centigrade), pH (2, 3.5, and 5), pressure, cake thickness (14, 20, 26, and 34 mm), air-blow time (2, 10 and 15 min) and filtration time were applied as input variables. The models' predictive accuracy was evaluated by the coefficient of determination (R2) parameter. The results revealed that the RFR model is superior to the SVR model for cake moisture prediction.

Image quality remains a key problem for both traditional and deep learning (DL)-based approaches to retinal image analysis, but identifying poor quality images can be time consuming and subjective. Thus, automated methods for retinal image quality scoring (RIQS) are needed. The current state-of-the-art is MCFNet, composed of three Densenet121 backbones each operating in a different colour space. MCFNet, and the EyeQ dataset released by the same authors, was a huge step forward for RIQS. We present QuickQual, a simple approach to RIQS, consisting of a single off-the-shelf ImageNet-pretrained Densenet121 backbone plus a Support Vector Machine (SVM). QuickQual performs very well, setting a new state-of-the-art for EyeQ (Accuracy: 88.50% vs 88.00% for MCFNet; AUC: 0.9687 vs 0.9588). This suggests that RIQS can be solved with generic perceptual features learned on natural images, as opposed to requiring DL models trained on large amounts of fundus images. Additionally, we propose a Fixed Prior linearisation scheme, that converts EyeQ from a 3-way classification to a continuous logistic regression task. For this task, we present a second model, QuickQual MEga Minified Estimator (QuickQual-MEME), that consists of only 10 parameters on top of an off-the-shelf Densenet121 and can distinguish between gradable and ungradable images with an accuracy of 89.18% (AUC: 0.9537). Code and model are available on GitHub: https://github.com/justinengelmann/QuickQual . QuickQual is so lightweight, that the entire inference code (and even the parameters for QuickQual-MEME) is already contained in this paper.