Conventional Machine Learning Approaches Research Articles

Guided quantum compression for high dimensional data classification

Quantum machine learning provides a fundamentally different approach to analyzing data. However, many interesting datasets are too complex for currently available quantum computers. Present quantum machine learning applications usually diminish this complexity by reducing the dimensionality of the data, e.g. via auto-encoders, before passing it through the quantum models. Here, we design a classical-quantum paradigm that unifies the dimensionality reduction task with a quantum classification model into a single architecture: the guided quantum compression model. We exemplify how this architecture outperforms conventional quantum machine learning approaches on a challenging binary classification problem: identifying the Higgs boson in proton-proton collisions at the LHC. Furthermore, the guided quantum compression model shows better performance compared to the deep learning benchmark when using solely the kinematic variables in our dataset.

Comparative Study of Conventional Machine Learning versus Deep Learning-Based Approaches for Tool Condition Assessments in Milling Processes

This evaluation of deep learning and traditional machine learning methods for tool state recognition in milling processes aims to automate furniture manufacturing. It compares the performance of long short-term memory (LSTM) networks, support vector machines (SVMs), and boosting ensemble decision trees, utilizing sensor data from a CNC machining center. These methods focus on the challenges and importance of feature selection, data preprocessing, and the application of tailored machine learning models to specific industrial tasks. Results show that SVM, with an accuracy of 96%, excels in handling high-dimensional data and robust feature extraction. In contrast, LSTM, which is appropriate for sequential data, is constrained by limited training data and the absence of pre-trained networks. Boosting ensemble decision trees also demonstrate efficacy in reducing model bias and variance. Conclusively, selecting an optimal machine learning strategy is crucial, depending on task complexity and data characteristics, highlighting the need for further research into domain-specific models to improve performance in industrial settings.

Comparative Study of Conventional Machine Learning versus Deep Learning-Based Approaches for Tool Condition Assessments in Milling Processes

This evaluation of deep learning and traditional machine learning methods for tool state recognition in milling processes aims to automate furniture manufacturing. It compares the performance of long short-term memory (LSTM) networks, support vector machines (SVMs), and boosting ensemble decision trees, utilizing sensor data from a CNC machining center. These methods focus on the challenges and importance of feature selection, data preprocessing, and the application of tailored machine learning models to specific industrial tasks. Results show that SVM, with an accuracy of 96%, excels in handling high-dimensional data and robust feature extraction. In contrast, LSTM, which is appropriate for sequential data, is constrained by limited training data and the absence of pre-trained networks. Boosting ensemble decision trees also demonstrate efficacy in reducing model bias and variance. Conclusively, selecting an optimal machine learning strategy is crucial, depending on task complexity and data characteristics, highlighting the need for further research into domain-specific models to improve performance in industrial settings.

Improving skin cancer detection by Raman spectroscopy using convolutional neural networks and data augmentation.

Our previous studies have demonstrated that Raman spectroscopy could be used for skin cancer detection with good sensitivity and specificity. The objective of this study is to determine if skin cancer detection can be further improved by combining deep neural networks and Raman spectroscopy. Raman spectra of 731 skin lesions were included in this study, containing 340 cancerous and precancerous lesions (melanoma, basal cell carcinoma, squamous cell carcinoma and actinic keratosis) and 391 benign lesions (melanocytic nevus and seborrheic keratosis). One-dimensional convolutional neural networks (1D-CNN) were developed for Raman spectral classification. The stratified samples were divided randomly into training (70%), validation (10%) and test set (20%), and were repeated 56 times using parallel computing. Different data augmentation strategies were implemented for the training dataset, including added random noise, spectral shift, spectral combination and artificially synthesized Raman spectra using one-dimensional generative adversarial networks (1D-GAN). The area under the receiver operating characteristic curve (ROC AUC) was used as a measure of the diagnostic performance. Conventional machine learning approaches, including partial least squares for discriminant analysis (PLS-DA), principal component and linear discriminant analysis (PC-LDA), support vector machine (SVM), and logistic regression (LR) were evaluated for comparison with the same data splitting scheme as the 1D-CNN. The ROC AUC of the test dataset based on the original training spectra were 0.886±0.022 (1D-CNN), 0.870±0.028 (PLS-DA), 0.875±0.033 (PC-LDA), 0.864±0.027 (SVM), and 0.525±0.045 (LR), which were improved to 0.909±0.021 (1D-CNN), 0.899±0.022 (PLS-DA), 0.895±0.022 (PC-LDA), 0.901±0.020 (SVM), and 0.897±0.021 (LR) respectively after augmentation of the training dataset (p<0.0001, Wilcoxon test). Paired analyses of 1D-CNN with conventional machine learning approaches showed that 1D-CNN had a 1-3% improvement (p<0.001, Wilcoxon test). Data augmentation not only improved the performance of both deep neural networks and conventional machine learning techniques by 2-4%, but also improved the performance of the models on spectra with higher noise or spectral shifting. Convolutional neural networks slightly outperformed conventional machine learning approaches for skin cancer detection by Raman spectroscopy.

Naive Bayes - Random Forest Ensemble Model Analysis and Heart Disease Prediction

Abstract: The critical task of accurately diagnosing heart disease can potentially save lives. Leveraging the UCI machine learning heart disease dataset and employing ensemble machine learning techniques, including Gausian Naive Bayes and Random Forest algorithms, the research investigates 13 primary characteristics to predict heart disease risks. The conventional machine learning approaches are utilized to analyze the dataset, unveiling correlations between features and heart infection risks. The aim is to develop a user-friendly interface, the Heart Disease Clinical Decision Support System (HDCDSS), where patients input their clinical details to receive a predictive analysis of their coronary disease. The system, built in Python with Flask and Bootstrap, provides clients with personalized reports on their heart health, enhancing diagnostic accuracy and potentiallystreamlining healthcare processes.

A Stochastic Regression and Sentiment Analysis-Based Approach for Forecasting Trends in the Stock Market

Stochastic regression problems especially applied to time series forecasting problems often encounter the challenge of volatility and unpredictable seasonality in datasets. One such application happens to forecasting the movement of stock markets globally. Stock data across the world exhibits an intrinsic baseline noise, which often can’t be correlated to previous temporal patterns. Rather, such divergences are an effect of multiple non-numeric variables which govern stock movement such as political scenarios, trade wars, imminent economic waxing and waning trends to name a few. However, it is essential to incorporate these factors while training a model so as to design a strongly sentient and anticipatory regression algorithm which is both pervasive and robust, encompassing as many numeric and non-numeric factors as possible. While conventional machine learning and deep learning approaches tend to leverage tested model architectures, they often miss out on the optimization of both training data and training method to yield potentially high forecasting accuracy. The paper combines stochastic regression in terms of momentum based training and data optimization which is shown to exhibit considerable lower forecasting error compared to existing approaches. To encompass a wider feature space, sentiment analysis has been incorporated to correlate stock movements with public opinions. The proposed approach has been tested on a multitude of benchmark datasets, to validate the performance of the approach. The mean absolute percentage error (MAPE) and regression values have been selected as primary metrics for the performance evaluation. The proposed approach attains a mean MAPE value of 3.22%. The analysis of the MAPE and forecasting accuracy w.r.t. existing benchmark approaches proves the improved forecasting performance of the proposed approach over a period of 300 days.

Deep Learning in Single-cell Analysis

Single-cell technologies are revolutionizing the entire field of biology. The large volumes of data generated by single-cell technologies are high dimensional, sparse, and heterogeneous and have complicated dependency structures, making analyses using conventional machine learning approaches challenging and impractical. In tackling these challenges, deep learning often demonstrates superior performance compared to traditional machine learning methods. In this work, we give a comprehensive survey on deep learning in single-cell analysis. We first introduce background on single-cell technologies and their development, as well as fundamental concepts of deep learning including the most popular deep architectures. We present an overview of the single-cell analytic pipeline pursued in research applications while noting divergences due to data sources or specific applications. We then review seven popular tasks spanning different stages of the single-cell analysis pipeline, including multimodal integration, imputation, clustering, spatial domain identification, cell-type deconvolution, cell segmentation, and cell-type annotation. Under each task, we describe the most recent developments in classical and deep learning methods and discuss their advantages and disadvantages. Deep learning tools and benchmark datasets are also summarized for each task. Finally, we discuss the future directions and the most recent challenges. This survey will serve as a reference for biologists and computer scientists, encouraging collaborations.

Enhancing flow stress predictions in CoCrFeNiV high entropy alloy with conventional and machine learning techniques

A machine learning technique leveraging artificial intelligence (AI) has emerged as a promising tool for expediting the exploration and design of novel high entropy alloys (HEAs) while predicting their mechanical properties at both room and elevated temperatures. In this paper, we predict the flow stress of hot-compressed CoCrFeNiV HEAs using conventional (qualitative and quantitative models) and advanced machine learning approaches across various temperature and strain rate conditions. Conventional modeling methods, including the modified Johnson-Cook (JC), modified Zerilli–Armstrong (ZA), and Arrhenius-type constitutive equations, are employed. Simultaneously, machine learning models are utilized to forecast flow stress under different hot working conditions. The performance of both conventional and machine learning models is evaluated using metrics such as coefficient of determination (R2), mean abosolute error (MAE), and root mean squared error (RMSE). The analysis reveals that the gradient boosting machine learning model shows superior prediction accuracy (with value R2 = 0.994, MAE = 7.77%, and RMSE = 9.7%) compared to conventional models and other machine learning approaches.

Cave mine pillar stability analysis using machine learning

The large scale of cave mines leads to many challenges, including operational logistics and geomechanics design. In current practice, pillar stability assessment relies almost exclusively on stress analysis. However, stability is also affected by other factors including those related to operational aspects of the mining method, the effects of which are difficult to account for during the design stages. In this paper we present a case study of the application of a machine learning approach to evaluate the influence of these operational factors on pillar stability at the Chuquicamata underground cave mine in northern Chile. Due to the likely multi-factorial damage process leading to collapses and considering the different pillar conditions, a tree-based machine learning method was used and analysed to improve the understanding of the relative importance of the various contributing factors. Unlike stress analysis methods, it does not require any a priori knowledge of failure mechanisms, nor the calibration of associated controlling parameters. The proposed random forest model predicted pillar collapses with 80% accuracy despite limited samples to model from. The main contributing factors to collapses were found to be related to available pillar volume, cave front geometry, and time under abutment stress conditions. The effects and interactions of such factors were also studied, showing that careful and improved control over operational conditions can significantly reduce the likelihood of pillar collapses. These conclusions could not have been obtained from stress analysis alone, illustrating the complementary nature of conventional stress analysis and machine learning approaches.

CTPredictor: A comprehensive and robust framework for predicting cell types by integrating multi-scale features from single-cell Hi-C data

Single-cell Hi-C (scHi-C) has emerged as a powerful technology for deciphering cell-to-cell variability in three-dimensional (3D) chromatin organization, providing insights into genome-wide chromatin interactions and their correlation with cellular functions. Nevertheless, the accurate identification of cell types across different datasets remains a formidable challenge, hindering comprehensive investigations into genome structure. In response, we introduce CTPredictor, an innovative computational method that integrates multi-scale features to accurately predict cell types in various datasets. CTPredictor strategically incorporates three distinct feature sets, namely, small intra-domain contact probability (SICP), smoothed small intra-domain contact probability (SSICP), and smoothed bin contact probability (SBCP). The resulting fusion classification model significantly enhances the accuracy of cell type prediction based on single-cell Hi-C data (scHi-C). Rigorous benchmarking against established methods and three conventional machine learning approaches demonstrates the robust performance of CTPredictor, positioning it as an advanced tool for cell type prediction within scHi-C data. Beyond its prediction capabilities, CTPredictor holds promise in illuminating 3D genome structures and their functional significance across a wide array of biological processes.

Functional link hybrid artificial neural network for predicting continuous biohydrogen production in dynamic membrane bioreactor

Conventional machine learning approaches have shown limited predictive power when applied to continuous biohydrogen production due to nonlinearity and instability. This study was aimed at forecasting the dynamic membrane reactor performance in terms of the hydrogen production rate (HPR) and hydrogen yield (HY) using laboratory-based daily operation datapoints for twelve input variables. Hybrid algorithms were developed by integrating particle swarm optimized with functional link artificial neural network (PSO-FLN) which outperformed other hybrid algorithms for both HPR and HY, with determination coefficients (R2) of 0.97 and 0.80 and mean absolute percentage errors of 0.014 % and 0.023 %, respectively. Shapley additive explanations (SHAP) explained the two positive-influencing parameters, OLR_added (1.1–1.3 mol/L/d) and butyric acid (7.5–16.5 g COD/L) supports the highest HPR (40–60 L/L/d). This research indicates that PSO-FLN model are capable of handling complicated datasets with high precision in less computational timeat 9.8 sec for HPR and 10.0 sec for HY prediction.

Deep Feature Extraction with Cubic-SVM for Classification of Brain Tumor

Brain tumors (BT) are fatal and debilitating conditions that shorten the typical lifespan of patients. Patients with BTs who receive inadequate treatment and an incorrect diagnosis have a lower chance of survival. Magnetic resonance imaging (MRI) is often employed to assess the tumor. However, because of the massive quantity of data provided by MRI, early BT detection is a complex and time-consuming procedure in biomedical imaging. As a consequence, an automated and efficient strategy is required. The detection of brain tumors or malignancies has been done using a variety of conventional machine learning (ML) approaches. The manually collected properties, however, provide the main problem with these models. The constraints previously stated are addressed by the fusion deep learning model for binary classification of BTs that is presented in this study. The recommended method combines two different CNN (Efficientnetb0, VGG-19) models that automatically extract features and make use of the feature’s classification using a Cubic SVM classifier model. Additionally, the recommended approach displayed outstanding performance in various classification measures, including Accuracy (99.78%), Precision (99.78%), Recall (99.78%), and F1-Score (99.78%), on the same Kaggle (Br35H) dataset. The proposed strategy performs better than current approaches for classifying BTs from MRI images.

A Comparative Study on Conventional Methods and Machine Learning Approaches on Stock Market Prediction

A Comparative Study on Conventional Methods and Machine Learning Approaches on Stock Market Prediction

Learning Analytics Model for Predictive Analysis of Learners Behavior for an Indigenous MOOC Platform (Tadakhul System) in Oman

The Massive Open Online Courses (MOOCs) platforms are widely used by the learner community all over the world. Using MOOC, the learners can choose the course of interest and learn it in their own pace. The main problem encountered in most MOOC based learning is the lack of a learning analytic system that monitors the learners’ interaction with their enrolled courses. This problem leads to incompletion or discontinuation of the course. In this paper, ‘Tadakul’ system, an original bilingual (English and Arabic) MOOC platform is developed for students of higher education institutions of the Sultanate of Oman. Using the Tadakhul system, learners of various higher education institutions of Oman can enroll themselves in various courses of their interest and complete the course at their own pace. This research aims in understanding the impact of learning analytics system used in the Tadakhul system. A novel deep-learning approach used in the system monitors the learning process of the learners based on their interaction with the enrolled courses. The feedback thus obtained, using the deep-learning approach, can be used to improve the student learning experience. To analyze the feedback obtained from the learners, an innovative approach of combining Bidirectional Long Short-Term Memory (BiLSTM) network with a Convolutional Neural Network (CNN) is proposed. The BiLSTM model performs well in analyzing the sequential data whereas the CNN model is good in extracting the spatial features at each hidden layer that are important for evaluating the student’s learning patterns. Thus the proposed model can identify learner’s learning behavior and learning styles that help teachers better understand the individual needs. The results of the experimental study revealed that the proposed model outperformed conventional machine learning approaches in predicting learner’s learning behavior. Hence, the results obtained by integrating BiLSTM and CNN models on the Tadakhul platform can improve the student experience by making teaching more efficient and effective.

Cervical Cancer Papsmear Classification through Meta-Learning Technique using Convolution Neural Networks.

This study uses convolutional neural networks (CNNs) and meta-learning techniques to create an accurate and efficient model for classifying the risk factors of cervical cancer. The dataset includes four types of cervical lesions, and the main objective is to categorize these lesions as either benign or malignant. This classification is essential for early and succesfull treatment of cervical cancer. The challenge arises from the complexity and variations in the images, resulting in the inability of conventional machine learning and deep learning approaches to provide correct classifications. Meta ensemble learning approaches are employed to improve the model's classification accuracy. The dataset of cervical cancer risk factors is preprocessed before being used to train and evaluate numerous CNNs utilizing pre-trained models and various architectures. Subsequently, a meta-learning is employed to optimize the learning process, and used to aggregate the outputs of the multiple CNNs. Moreover, the assessment findings show the model achieves high accuracy and effectiveness. Finally, the suggested model's accuracy score will be contrasted against the current cutting-edge methods used by other existing systems.

Internet of things‐enabled intelligent systems for remote chronic disease monitoring

AbstractThe possibility of remotely monitoring and managing chronic diseases is made feasible by the Internet of Things (IoT), which enables the collection and analysis of vast amounts of data from various sources such as sensors, devices, and wearables. However, conventional machine learning approaches often encounter difficulties when dealing with IoT data due to its noise, heterogeneity, and high dimensions. In this study, we introduce a novel technique for developing human‐centric intelligent systems for remote monitoring of chronic diseases using deep learning in an IoT context. This technique is capable of handling complex and diverse IoT data, providing accurate and comprehensible predictions and recommendations. We outline a standardized architecture for these systems, comprising of three distinct phases: data acquisition, data processing, and data visualization. To demonstrate the effectiveness of our methodology, we apply it to a case study involving the development and evaluation of a human‐centered intelligent system for remote monitoring of hypertension and diabetic patients, involving real users. Our findings reveal a substantial enhancement in prediction accuracy when employing our proposed hybrid algorithm. When compared to traditional algorithms, our proposed hybrid algorithm exhibits superior performance, achieving an accuracy of 93.5%, surpassing the Restricted Boltzmann Machine (RBM) with an accuracy of 88.2%, Long Short‐Term Memory (LSTM) networks at 90.4%, and Convolutional Neural Networks (CNN) at 91.6%. This improvement in accuracy is critical for ensuring reliable disease monitoring and management, highlighting the effectiveness of our approach. In terms of precision, scalability, and user satisfaction, we demonstrate the effectiveness and efficiency of our method. Furthermore, we address the social and ethical implications inherent in our methodology and suggest avenues for future research in this domain.

MOF-GRU: A MOFid-Aided Deep Learning Model for Predicting the Gas Separation Performance of Metal-Organic Frameworks.

The remarkable versatility of metal-organic frameworks (MOFs) stems from their rich chemical information, leading to numerous successful applications. However, identifying optimal MOFs for specific tasks necessitates a thorough assessment of their chemical attributes. Conventional machine learning approaches for MOF prediction have relied on intricate chemical and structural details, hampering rapid evaluations. Drawing inspiration from recent advancements exemplified by Snurr et al., wherein a text string was used to represent a MOF (MOFid), we introduce a MOFid-aided deep learning model, named the MOF-GRU model. This model, founded on natural language processing principles and utilizing the gated recurrent unit architecture, leverages the serialized text string representation of metal-organic frameworks (MOFs) to forecast gas separation performance. Through a focused study on CH4/N2 separation, we substantiate the efficacy of this approach. Comparative assessments against traditional machine learning techniques underscore our model's superior predictive accuracy and its capacity to handle extensive data sets adeptly. The MOF-GRU model remarkably uncovers latent structure-performance relationships with only MOF sequences, obviating the necessity for intricate three-dimensional (3D) structural information. Overall, this model's judicious design empowers efficient data utilization, thereby hastening the discovery of high-performance materials tailored for gas separation applications.

Indoor Plant Soil-Plant Analysis Development (SPAD) Prediction Based on Multispectral Indices and Soil Electroconductivity: A Deep Learning Approach

Leaf Soil-Plant Analysis Development (SPAD) prediction is a crucial measure of plant health and is essential for optimizing indoor plant management. The deep learning methods offer advanced tools for precise evaluations but their adaptation to the heterogeneous indoor plant ecosystem presents distinct challenges. This study assesses how accurately deep neural network (DNN) predicts SPAD values in leaves on indoor plants when compared to well-established machine learning techniques, including Random Forest (RF) and Extreme Gradient Boosting (XGB). The covariates for prediction were based on low-cost multispectral and soil electro-conductivity (EC) sensors, enabling a non-destructive sensing approach. The study also strongly emphasized multicollinearity analysis quantified by the Variance Inflation Factor (VIF) and two independent indices, as well as its effect on prediction accuracy using deep and machine learning methods. DNN resulted in higher accuracy to RF and XGB, also performing better using filtered data after multicollinearity analysis based on the coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE) (R2 = 0.589, RMSE = 11.68, MAE = 9.52) in comparison to using all input covariates (R2 = 0.476, RMSE = 12.90, MAE = 10.94). Overall, DNN was proven as a more accurate prediction method than the conventional machine learning approach for the prediction of leaf SPAD values in indoor plants, despite using heterogenous plant types and input covariates.

ETCNet: An EEG-based motor imagery classification model combining efficient channel attention and temporal convolutional network

Brain-computer interface (BCI) enables the control of external devices using signals from the brain, offering immense potential in assisting individuals with neuromuscular disabilities. Among the different paradigms of BCI systems, the motor imagery (MI) based electroencephalogram (EEG) signal is widely recognized as exceptionally promising. Deep learning (DL) has found extensive applications in the processing of MI signals, wherein convolutional neural networks (CNN) have demonstrated superior performance compared to conventional machine learning (ML) approaches. Nevertheless, challenges related to subject independence and subject dependence persist, while the inherent low signal-to-noise ratio of EEG signals remains a critical aspect that demands attention. Accurately deciphering intentions from EEG signals continues to present a formidable challenge. This paper introduces an advanced end-to-end network that effectively combines the efficient channel attention (ECA) and temporal convolutional network (TCN) components for the classification of motor imagination signals. We incorporated an ECA module prior to feature extraction in order to enhance the extraction of channel-specific features. A compact convolutional network model uses for feature extraction in the middle part. Finally, the time characteristic information is obtained by using TCN. The results show that our network is a lightweight network that is characterized by few parameters and fast speed. Our network achieves an average accuracy of 80.71% on the BCI Competition IV-2a dataset.

The Effect of Image Size on the Deep Learning Approach for Classifying Covid-19 Pneumonia

The scope of this study is related to the classification of covid-19 pneumonia which uses X-ray images of the lungs as input and is then classified into 3 categories, namely normal (healthy), pneumonia, and covid-19 pneumonia. The classification process uses a deep learning approach, which is becoming a trend nowadays because its performance is better than conventional machine learning approaches. The image dataset in this study is a collection of X-ray images of the lungs consisting of 1,525 normal images, 1,525 pneumonia images, and 1,525 Covid-19 pneumonia images. These images vary in size, but all images are larger than 1000x1000 pixels. The large size of the image makes the training time long and the computational resources required are large. Deep learning machines need to reduce the size of the image to make the process more effective. However, changes in image size may affect classification performance. Therefore, we conducted experiments in this study to determine the effect of image size changes on the classification performance of COVID-19 pneumonia using a deep learning approach. We use the Convolutional Neural Network method, which uses 22 layers with 5 convolution layers, for classification. The experimental results show that the size of the input image affects the classification performance of covid-19 pneumonia. This study provides important information that larger image sizes do not always result in better classification performance. In addition, the image size that is too small causes very low classification performance. The performance of the classification of covid-19 pneumonia using the CNN method shows the most optimal results at an input image size of 500x500 pixels.