In this work, we conduct a comparative analysis of Machine Learning (ML) and Deep Learning (DL) approaches for solar irradiation forecasting at Batna station. Specifically, we examine six different ML methods: Linear Regression (LR), Multilayer Perceptron (MLP), Extreme Learning Machine (ELM), Kernel Ridge Regression (KRR), Support Vector Regression (SVR), and Gaussian Process Regression (GPR). Furthermore, we investigate a deep learning-based regression approach considered a relatively recent field technique. We propose to use three DL methods, namely Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Bi-directional Long Short-Term Memory (Bi-LSTM). We present and discuss the experimental outcomes obtained from the Batna station data.

In the evolving world of robotics, the way humans and robots interact plays a crucial role in the overall system performance and user experience. Traditionally, robotic control for accomplishing tasks have been dominated by programming languages like ROBOFORTH or touchpad interfaces. However, these methods often create barriers to user interaction. This study explores the potential of hand gesture recognition, specifically focusing on the deep-learning MediaPipe library’s real-time hand-landmark detection capabilities. We present a system that combines MediaPipes abilities with controlling the ST Robotics R12 robot, allowing real-time hand gestures to be translated into robotic drawing actions and tasks. This integration offers a natural and interactive communication medium that could revolutionize how humans carry out tasks with robots. By leveraging MediaPipes computer vision and deep learning techniques, we successfully controlled the R12 robot through gesture-based interactions. The system effectively translated hand gestures into robotic drawing functions and specific tasks such as object relocation. However, future improvements should concentrate on enhancing precision, reevaluating reliance on ROBOFORTH and exploring MATLAB Simulink’s potential for advanced gesture-based control algorithms.

The determination of the octane number plays a major role in quantifying the quality of gasoline. The standard method, the international standard ASTM-CFR internal combustion engine, used for this purpose suffers from its high cost and time. Many algorithms have been developed to address the limitations of this method, taking advantage of infrared spectroscopy, which provides easily measurable parameters that can be used to predict the octane number. This paper proposes two methods to compete with three existing algorithms (ELM, IELM, and SaDE-ELM) and also aims at achieving high accuracy results compared to the engine-based measurement method. The proposed methods used ensemble learning strategy combined with ELM instead of single ELM learner, used in the aforementioned algorithms, to achieve better predictions of the octane number. The findings indicate our algorithms outperformed the existing algorithms and the predictions are very close to that of the standard method. This can be considered an important achievement in the field of octane number prediction that can eventually replace the standard method. Also, contrary to the common belief that Boosting algorithms are superior to Bagging algorithms, in this paper, we demonstrated that our Bagging algorithm performed almost identically compared with the Boosting algorithm. Despite these promising results, further research should be undertaken to investigate the Hughes effect phenomenon that the gasoline data set, used in this work, suffer from.

In this work, we propose a new algorithm to improve existing techniques used in the field of spectroscopic data regression analysis. In particular, it combines the power of nonlinear kernel regressors (kernel ridge regression [KRR], kernel principal component regression [KPCR], and Gaussian process regression [GPR]) with an optimization based on nondominated sorting multi-objective genetic algorithm (NSGAII) to filter the residual outliers in the prediction space and leverage points in the features space. The proposed algorithm, contrary to most existing robust algorithms, simultaneously optimizes many complementary objectives for an automatic adaptation and thus a better outliers detection. It is well known that the elimination of outliers greatly improves the regression model. It is thus the aim of this work to develop a new robust regression algorithm. It has been applied on five different datasets, and the results are compared to both classical nonlinear regression methods and the commonly used robust regression methods robust continuum regression (RCR), partial robust M-regression (PRM), robust principal component regression (RPCR), robust PLSR (RSIMPLS), and locally weighted regression (LWR). They show that the proposed algorithm outperforms the classical nonlinear regression methods and is a promising competitor to the robust methods outperforming most of them. Even though the results obtained are only from five datasets, this algorithm can be considered an interesting contribution for improving data analysis in the field of chemometrics.

Support vector machines (SVMs) are a popular class of supervised learning algorithms, and are particularly applicable to large and high-dimensional classification problems. Like most machine learning methods for data classification and information retrieval, they require manually labeled data samples in the training stage. However, manual labeling is a time consuming and errorprone task. One possible solution to this issue is to exploit the large number of unlabeled samples that are easily accessible via the internet. This paper presents a novel active learning method for text categorization. The main objective of active learning is to reduce the labeling effort, without compromising the accuracy of classification, by intelligently selecting which samples should be labeled. The proposed method selects a batch of informative samples using the posterior probabilities provided by a set of multi-class SVM classifiers, and these samples are then manually labeled by an expert. Experimental results indicate that the proposed active learning method significantly reduces the labeling effort, while simultaneously enhancing the classification accuracy.

The machine learning approaches to text categorization proceed by teaching the system how to classify through labeled samples. In real application scenarios, the collection of training (labeled) samples to design a classifier is not always trivial due to the complexity and the cost which characterize the process. A possible solution to this issue can be found in the exploitation of the large number of unlabeled samples which are accessible at zero cost from the web. Active learning strives to reduce the required labeling effort while retaining the accuracy by intelligently selecting the samples to be labeled. This Study presents a novel active learning method for text classification that selects a batch of informative samples for manual labeling by an expert. The proposed method uses the posterior probability output of a multi-class SVM method. The experiments are performed with two well-known datasets and the presented experimental results show that employing our active learning method can significantly reduce the need for labeled training data.

The key idea behind active learning is that if the learning method is allowed to choose the data to learn from, the amount of data needed for the training phase can be significantly reduced. Thus, the cost of manual annotating the data will be less, and the process of learning can be accelerated. Most of the studies on applying active learning methods to automatic text classification focused on requesting the label of a single unlabeled document in each iteration. Unlike English, There are very few researches done in this area for the Arabic text. In this paper, we present a novel active learning method for Arabic text classification using multi-class SVM. The proposed method selects a batch of informative samples for manually labeling by an expert. The experimental results show that employing our method can significantly reduce the need for labeled training data.

In this paper, a novel method for semisupervised classification with limited training samples is presented. Its aim is to exploit unlabeled data available at zero cost in the image under analysis for improving the accuracy of a classification process based on support vector machines (SVMs). It is based on the idea to augment the original set of training samples with a set of unlabeled samples after estimating their label. The label estimation process is performed within a multiobjective genetic optimization framework where each chromosome of the evolving population encodes the label estimates as well as the SVM classifier parameters for tackling the model selection issue. Such a process is guided by the joint minimization of two different criteria which express the generalization capability of the SVM classifier. The two explored criteria are an empirical risk measure and an indicator of the classification model sparseness, respectively. The experimental results obtained on two multisource remote sensing data sets confirm the promising capabilities of the proposed approach, which allows the following: (1) taking a clear advantage in terms of classification accuracy from unlabeled samples used for inflating the original training set and (2) solving automatically the tricky model selection issue.

In this paper, we propose a novel method that aims at assisting the ground-truth expert through an automatic detection of potentially mislabeled learning samples. This method is based on viewing the mislabeled sample detection issue as an optimization problem where it is looked for the best subset of learning samples in terms of statistical separability between classes. This problem is formulated within a genetic optimization framework, where each chromosome represents a candidate solution for validating/invalidating the learning samples collected by the ground-truth expert. The genetic optimization process is guided by the joint optimization of two different criteria which are the maximization of a between-class statistical distance and the minimization of the number of invalidated samples. Experiments conducted on both simulated and real data sets show that the proposed ground-truth validation method succeeds in the following: 1) in detecting the mislabeled samples with a high accuracy, even when up to 30% of the learning samples are mislabeled, and 2) in strongly limiting the negative impact of the mislabeling issue on the accuracy of the classification process.

In this paper, we propose a novel genetic method that aims at providing the ground-truth expert with a binary information of the kind "validated"/"invalidated" for each ground-truth (learning) sample collected. For each invalidated sample, the expert may confirm or not the invalidation, and thus correct or maintain the adopted labeling before creating the final learning set that will be exploited in the classification process. Experimental results confirm the effectiveness of the proposed method in correctly detecting mislabeled learning samples and thus in limiting their negative impact on the classification process.

The updating of classification maps, as new image acquisitions are obtained, raises the problem of ground-truth information (training samples) updating. In this context, semisupervised multitemporal classification represents an interesting though still not well consolidated approach to tackle this issue. In this letter, we propose a novel methodological solution based on this approach. Its underlying idea is to update the ground-truth information through an automatic estimation process, which exploits archived ground-truth information as well as basic indications from the user about allowed/forbidden class transitions from an acquisition date to another. This updating problem is formulated by means of the support vector machine classification approach and a constrained multiobjective optimization genetic algorithm. Experimental results on a multitemporal data set consisting of two multisensor (Landsat-5 Thematic Mapper and European Remote Sensing satellite synthetic aperture radar) images are reported and discussed.

This work aims at proposing a methodological solution to the challenging problem of semi-supervised classification map updating. The underlying idea of the proposed method is to update automatically the ground-truth information that will be exploited to train a support vector machine (SVM) classifier for the image under analysis. Such updating problem is formulated within a constrained multiobjective genetic algorithm (MOGA) which makes use of temporal information provided by the user under the form of allowed/forbidden class transitions. Experimental results on a multitemporal data set consisting of two multisensor (Landsat-5 TM and ERS-1 SAR) images are reported and discussed.

In this paper, we propose a novel approach based on multiobjective genetic algorithms for SVM classifiers applied to problems with limited training samples. It consists in injecting unlabeled samples into the training set after finding their optimal label through a genetic optimization process. Such process looks for the best chromosome which encodes the sample labels relying on two fitness functions that estimate the SVM classifier generalization performance. The chromosome is configured in such a way as to solve also the SVM model selection issue. The choice of the two fitness criteria is made so that to satisfy two requirements which are the sparseness of the SVM solution and the statistical compatibility with the available training samples. Experiments conducted on the basis of a multispectral image show the promising capability of the proposed approach to integrate unlabeled samples in the SVM classification process with significant gains of accuracy.