Learning-based Approach Research Articles

Deep learning enabled rapid classification of yeast species in food by imaging of yeast microcolonies.

Diverse species of yeasts are commonly associated with food and food production environments. The contamination of food products by spoilage yeasts poses significant challenges, leading to quality degradation and food loss. Similarly, the introduction of undesirable strains during fermentation can cause considerable challenges with the quality and progress of the fermentation process. Conventional detection methods require the isolation of visible yeast colonies for genetic or biochemical characterization, which takes 5-7days and demands significant labor. This study presents a deep learning-based yeast classification approach that combines conventional cultivation methods, white light optical microscopy of microcolony, and deep learning techniques for rapidly detecting and classifying yeasts. Utilizing deep convolutional neural networks, the model accurately discriminates 7 different yeasts within 6h, achieving a mPrecision of 96.0% and a mRecall of 96.3%. Synthetic image dataset generated by generative adversarial networks (GAN) model further improved the model performance for Debaryomyces hansenii and Wickerhamomyces anomalus, yeast species with lower initial classification performance. With the addition of synthetic images in the training process, Precision for W. anomalus and Recall for D. hansenii increased by 7.7% and 5.6%, respectively. The yeast classification model was validated in the presence of microscopic food debris using tomato and tomato juice as representative examples of fresh produce and processed juice. The model maintained high classification accuracy in the presence of food debris (mPrecision and mRecall >93.9%). Overall, this methodology significantly accelerates the detection and classification of yeast species using conventional cultivation and simple white light microscopy in combination with deep learning. The simplicity, including low cost of the experimental approaches and the robustness of the deep learning model make it a highly applicable approach for routine yeast monitoring and yeast spoilage control in the food industry.

A machine learning-based hybrid approach for maximizing supply chain reliability in a pharmaceutical supply chain

A machine learning-based hybrid approach for maximizing supply chain reliability in a pharmaceutical supply chain

A multi-objective reinforcement learning-based velocity optimization approach for electric trucks considering battery degradation mitigation

A multi-objective reinforcement learning-based velocity optimization approach for electric trucks considering battery degradation mitigation

Study on the predictability of new topics of scholars: A machine learning-based approach using knowledge networks

Study on the predictability of new topics of scholars: A machine learning-based approach using knowledge networks

ECCDN-Net: A deep learning-based technique for efficient organic and recyclable waste classification.

Efficient waste management is essential to minimizing environmental harm as well as encouraging sustainable progress. The escalating volume and sophistication of waste present significant challenges, prompting innovative methods for effective waste categorization and management. Deep learning models have become highly intriguing tools for automating trash categorization activities, providing effective ways to optimize processes for handling waste. Ourwork presents a novel deep learning method for trash classification, with the goal to improve the accuracy, also efficiency of garbage image categorization. We examined the effectiveness of several pre-trained models, such as InceptionV2, Densenet201, MobileNet v2, and Resnet18, using objective evaluation and cross-validation. We proposed an Eco Cycle Classifier Deep Neural Network (ECCDN-Net) model that is particularly built for the categorization of waste images. ECCDN-Net utilizes the advantageous qualities of Densenet201 and Resnet18 by merging their capacities to extract features, enhanced with auxiliary outputs to optimize the classification procedure. The set of imagesused in this study comprises 24,705 images that are divided into two distinct classes: Organic and Recyclable. The set allows extensive evaluation and training of deep learning models for waste classification of images tasks. Our research demonstrates that the ECCDN-Net model classifies waste images with 96.10% accuracy, outperforming other pre-trained models. Resnet18 had 92.68% accuracy, MobileNet v2 93.27%, Inception v3 94.77%, and Densenet201, a significant improvement, 95.98%. ECCDN-Net outperformed these models in waste image categorization with 96.10% accuracy. We ensure the reliability and generalizability of our methods throughout the dataset by integrating and cross-validating deep learning models. The current work introduces an innovative deep learning-based approach that has promising potential for waste categorization and management strategies.

GraphCC: A practical graph learning-based approach to Congestion Control in datacenters

GraphCC: A practical graph learning-based approach to Congestion Control in datacenters

Prognostic models for progression-free survival in atypical meningioma: Comparison of machine learning-based approach and the COX model in an Asian multicenter study.

Atypical meningiomas are prevalent intracranial tumors with varied prognoses and recurrence rates. The role of adjuvant radiotherapy (ART) in atypical meningiomas remains debated. This study aimed to develop and validate a prognostic model incorporating machine learning techniques and clinical factors to predict progression-free survival (PFS) in patients with atypical meningiomas and assess the impact of ART. A retrospective review of 669 patients from five institutions in Korea and China was conducted. Cox proportional hazards, gradient boosting machine, and random survival forest models were employed for comparative analysis, utilizing both internal and external validation sets. Model performance was assessed using Harrell's concordance index and permutation feature importance. Of 581 eligible patients, age, post-operative platelet count, performance status, Simpson grade, and ART were identified as significant prognostic factors across all models. In the ART subgroup, age and tumor size were the top prognostic indicators. The Cox model outperformed other methods, achieving a training C-index of 0.73 (95 % CI: 0.72-0.73) and an external validation C-index of 0.74 (95 % CI: 0.73-0.74). The model effectively stratified patients into risk categories, revealing a differential impact of ART: low-risk patients in the active surveillance group showed a 5.6 % improvement in 5-year PFS with predicted ART addition, compared to a 15.9 % improvement in the high-risk group. This multicenter study offers a validated prognostic model for atypical meningiomas, highlighting the need for tailored treatment plans. The model's ability to stratify patients into risk categories for PFS provides a valuable tool for clinical decision-making, potentially optimizing patient outcomes.

Object Detection & Analysis with Deep CNN and Yolov8 in Soft Computing Frameworks

Object detection is one of the major roles in deep learning and soft computing which contributes to many real time cases in healthcare, agriculture etc. This study proposes a deep learning-based approach for object detection to detect lung cancer and diagnosis by utilizing deep Convolutional Neural Networks (CNN) and the YOLOv8 model, with DICOM (Digital Imaging and Communications in Medicine) images for robust image analysis. Lung cancer remains one of the leading causes of mortality worldwide, necessitating early and accurate detection to improve patient outcomes. The primary objective of the research is to enhance the accuracy, precision, and recall rates in lung cancer detection, while reducing false positives and false negatives, through advanced machine learning techniques. In the proposed work, CNN is employed for feature extraction, enabling the model to capture the intricate patterns present in the DICOM images. YOLOv8, a cutting-edge object detection algorithm, is integrated to detect cancerous regions with high efficiency and speed. A comparative analysis is conducted with traditional machine learning classifiers such as Support Vector Machine (SVM), AdaBoost, Random Forest, and K-Nearest Neighbors (KNN), demonstrating the superior performance of the proposed deep learning models. The experimental results reveal that the CNN-YOLOv8 model achieves remarkable accuracy of 94 Parsant, with a precision of 93.56 Parsant, recall of 92 Parsant, ROC score of 93 Parsant, and an F-score of 94.60 Parsant. These findings underscore the effectiveness of deep learning in lung cancer detection, significantly outperforming conventional models in terms of accuracy and reliability. The novelty of this research lies in the integration of CNN with YOLOv8, specifically optimized for medical DICOM images, which allows for real-time, accurate identification of lung cancer while maintaining computational efficiency.

Enhancing Telexistence Control Through Assistive Manipulation and Haptic Feedback

The COVID-19 pandemic brought telepresence systems into the spotlight, yet manually controlling remote robots often proves ineffective for handling complex manipulation tasks. To tackle this issue, we present a machine learning-based assistive manipulation approach. This method identifies target objects and computes an inverse kinematic solution for grasping them. The system integrates the generated solution with the user’s arm movements across varying inverse kinematic (IK) fusion levels. Given the importance of maintaining a sense of body ownership over the remote robot, we examine how haptic feedback and assistive functions influence ownership perception and task performance. Our findings indicate that incorporating assistance and haptic feedback significantly enhances the control of the robotic arm in telepresence environments, leading to improved precision and shorter task completion times. This research underscores the advantages of assistive manipulation techniques and haptic feedback in advancing telepresence technology.

Analyzing Drill Core Logging Using Rock Quality Designation–60 Years’ Experience from Modifications to Applications

The accurate analysis of rock cores is of primary importance for designing in and on the rock mass environment. There are several methods for analyzing boreholes, but the most accepted and widely used method is the rock quality designation (RQD) value, which has been a core rating metric for six decades. The RQD value serves as: (1) an important input parameter for rock mass classifications such as RMR and Q; (2) a basis for calculating the Geological Strength Index (GSI) of boreholes; and (3) a key indicator in assessing rock mass quality, particularly in highly fractured or weak rock masses. The original RQD method has several drawbacks and shortcomings, which have led to numerous proposed amendments. This review paper aims to: (1) summarize alternative methods of calculating the RQD value; (2) analyze the sensitivity of different rock mass classifications to the accuracy of this value; and (3) present a systematic analysis of the practical implications of modified RQD methods, emphasizing advancements such as DFN modeling, seismic RQD techniques, and machine learning-based approaches. The findings provide a comprehensive framework for more robust and versatile assessments of rock mass quality.

Machine Learning-Based Approaches for Breast Density Estimation from Mammograms: A Comprehensive Review

Breast cancer, as of 2022, is the most prevalent type of cancer in women. Breast density—a measure of the non-fatty tissue in the breast—is a strong risk factor for breast cancer that can be estimated from mammograms. The importance of studying breast density is twofold. First, high breast density can be a factor in lowering mammogram sensitivity, as dense tissue can mask tumors. Second, higher breast density is associated with an increased risk of breast cancer, making accurate assessments vital. This paper presents a comprehensive review of the mammographic density estimation literature, with an emphasis on machine-learning-based approaches. The approaches reviewed can be classified as visual, software-, machine learning-, and segmentation-based. Machine learning methods can be further broken down into two categories: traditional machine learning and deep learning approaches. The most commonly utilized models are support vector machines (SVMs) and convolutional neural networks (CNNs), with classification accuracies ranging from 76.70% to 98.75%. Major limitations of the current works include subjectivity and cost-inefficiency. Future work can focus on addressing these limitations, potentially through the use of unsupervised segmentation and state-of-the-art deep learning models such as transformers. By addressing the current limitations, future research can pave the way for more reliable breast density estimation methods, ultimately improving early detection and diagnosis.

Machine Learning-Based Spectral Analyses for Camellia japonica Cultivar Identification

Camellia japonica is a plant species with high cultural and biological relevance. Besides being used as an ornamental plant species, C. japonica has relevant biological properties. Due to hybridization, thousands of cultivars are known, and their accurate identification is mandatory. Infrared spectroscopy is currently recognized as an accurate and rapid technique for species and/or subspecies identifications, including in plants. However, selecting proper analysis tools (spectra pre-processing, feature selection, and chemometric models) highly impacts the accuracy of such identifications. This study tests the impact of two distinct machine learning-based approaches for discriminating C. japonica cultivars using near-infrared (NIR) and Fourier transform infrared (FTIR) spectroscopies. Leaves infrared spectra (NIR—obtained in a previous study; FTIR—obtained herein) of 15 different C. japonica cultivars (38 plants) were modeled and analyzed via different machine learning-based approaches (Approach 1 and Approach 2), each combining a feature selection method plus a classifier application. Regarding Approach 1, NIR spectroscopy emerged as the most effective technique for predicting C. japonica cultivars, achieving 81.3% correct cultivar assignments. However, Approach 2 obtained the best results with FTIR spectroscopy data, achieving a perfect 100.0% accuracy in cultivar assignments. When comparing both approaches, Approach 2 also improved the results for NIR data, increasing the correct cultivar predictions by nearly 13%. The results obtained in this study highlight the importance of chemometric tools in analyzing infrared data. The choice of a specific data analysis approach significantly affects the accuracy of the technique. Moreover, the same approach can have varying impacts on different techniques. Therefore, it is not feasible to establish a universal data analysis approach, even for very similar datasets from comparable analytical techniques.

Deep Learning Approach For Suspicious Activity Detection from Surveillance Video in Examination Hall

This paper presents a deep learning-based approach for detecting suspicious activities in examination halls using surveillance video. The traditional methods of monitoring students during examinations have limitations, particularly when it comes to real-time detection and alerting. To address this issue, a system is proposed that employs computer vision and deep learning techniques to identify suspicious behaviors such as cheating, unauthorized movements, or distractions. The system processes video feeds from surveillance cameras, analyzes the actions of students, and triggers real-time alerts when abnormal behavior is detected. Experimental results show that the proposed system can detect suspicious activities with high accuracy, providing an automated and reliable mechanism for monitoring exam environments. This paper highlights the potential of deep learning to enhance security and integrity in educational settings

A comparative analysis and prediction of carbon emission in India using Machine learning models

<p style="line-height:150%;text-align:justify;text-indent:36.0pt;"><span style="background-color:yellow;font-family:"Times New Roman","serif";font-size:12.0pt;line-height:150%;">Among the most significant issues that will impact and pose a major threat to our future are global warming and climate change. This study focuses on forecasting India's carbon emissions, specifically examining the role of agriculture and agri-related industries, using time-series data from 1990 to 2020. </span><span style="background-color:lime;font-family:"Times New Roman","serif";font-size:12.0pt;line-height:150%;">To achieve this, a machine learning-based approach was proposed, utilizing five advanced models AdaBoost, XGB, Gradient Boosting, Random Forest, and Linear Regression. These models were selected for their ability to process large datasets, identify complex patterns, and provide precise predictions, offering a comprehensive framework for estimating carbon emissions. The approach aims to identify the most accurate predictive model for estimating carbon emissions, facilitating informed policy interventions and strategic planning. </span><span style="background-color:aqua;font-family:"Times New Roman","serif";font-size:12.0pt;line-height:150%;">The Carbon Budget 2023 research highlights that India's carbon emissions increased by 8.2% in 2023, raising significant concerns for environmental sustainability. Using the proposed machine learning models, the study facilitates robust data prediction. Among the five models, XGB demonstrates superior performance with evaluation metrics such as a Mean Absolute Error (MAE) of 19843, Root Mean Square Error (RMSE) of 24022, Mean Squared Error (MSE) of 5770998, R² value of 0.9, and test accuracy of 99%. These findings establish XGB as the most reliable model for forecasting carbon emissions. Consequently, XGB emerges as a powerful tool for accurately estimating emissions and addressing the challenges posed by climate change.</span></p>

Machine Learning-Based Grading of Engine Health for High-Performance Vehicles

This paper presents a machine learning-based approach to grade engine health and generate a respective score ranging from 0 to 100 for tuned high-performance vehicles. It integrates the technical intricacies of automotive engineering with machine learning practices in a clear and sequential process. Data are collected from sensors monitoring revolutions per minute, boost, rail pressure, timing, and temperature. The data are processed for supervised learning and analyzed using visualizations such as a heatmap and t-SNE plots. Models are trained, innovatively tuned through hyperparameter optimization, and tested for their ability to grade new data logs. The results highlight K-Neighbors, Extra Trees, and Extreme Gradient Boosting as exceptional regressors for this task. The automated grading of engine health and performance enhances objectivity and efficiency in the tuning process and potentially serves as a basis for a digital twin. The developed methodology is discussed in the context of health evaluation for any sensor-based system, with practical applications extending across various domains and industries.

Efficient and Effective Detection of Repeated Pattern from Fronto-Parallel Images with Unknown Visual Contents

The effective detection of repeated patterns from inputs of unknown fronto-parallel images is an important computer vision task that supports many real-world applications, such as image retrieval, synthesis, and texture analysis. A repeated pattern is defined as the smallest unit capable of tiling the entire image, representing its primary structural and visual information. In this paper, a hybrid method is proposed, overcoming the drawbacks of both traditional and existing deep learning-based approaches. The new method leverages deep features from a pre-trained Convolutional Neural Network (CNN) to estimate initial repeated pattern sizes and refines them using a dynamic autocorrelation algorithm. Comprehensive experiments are conducted on a new dataset of fronto-parallel textile images as well as another set of real-world non-textile images to demonstrate the superiority of the proposed method. The accuracy of the proposed method is 67.3%, which represents 20% higher than the baseline method, and the time cost is only 11% of the baseline. The proposed method has been applied and contributed to textile design, and it can be adapted to other applications.

Predicting Asthma Hospitalizations from Climate and Air Pollution Data: A Machine Learning-Based Approach

This study explores the predictability of monthly asthma notifications using models built from different machine learning techniques in Maceió, a municipality with a tropical climate located in the northeast of Brazil. Two sets of predictors were combined and tested, the first containing meteorological variables and pollutants, called exp1, and the second only meteorological variables, called exp2. For both experiments, tests were also carried out incorporating lagged information from the time series of asthma records. The models were trained on 80% of the data and validated on the remaining 20%. Among the five methods evaluated—random forest (RF), eXtreme Gradient Boosting (XGBoost), Multiple Linear Regression (MLR), support vector machine (SVM), and K-nearest neighbors (KNN)—the RF models showed superior performance, notably those of exp1 when incorporating lagged asthma notifications as an additional predictor. Minimum temperature and sulfur dioxide emerged as key variables, probably due to their associations with respiratory health and pollution levels, emphasizing their role in asthma exacerbation. The autocorrelation of the residuals was assessed due to the inclusion of lagged variables in some experiments. The results highlight the importance of pollutant and meteorological factors in predicting asthma cases, with implications for public health monitoring. Despite the limitations presented and discussed, this study demonstrates that forecast accuracy improves when a wider range of lagged variables are used, and indicates the suitability of RF for health datasets with complex time series.

Deep Learning-Based Multi-View Projection Synthesis Approach for Improving the Quality of Sparse-View CBCT in Image-Guided Radiotherapy.

While radiation hazards induced by cone-beam computed tomography (CBCT) in image-guided radiotherapy (IGRT) can be reduced by sparse-view sampling, the image quality is inevitably degraded. We propose a deep learning-based multi-view projection synthesis (DLMPS) approach to improve the quality of sparse-view low-dose CBCT images. In the proposed DLMPS approach, linear interpolation was first applied to sparse-view projections and the projections were rearranged into sinograms; these sinograms were processed with a sinogram restoration model and then rearranged back into projections. The sinogram restoration model was modified from the 2D U-Net by incorporating dynamic convolutional layers and residual learning techniques. The DLMPS approach was trained, validated, and tested on CBCT data from 163, 30, and 30 real patients respectively. Sparse-view projection datasets with 1/4 and 1/8 of the original sampling rate were simulated, and the corresponding full-view projection datasets were restored via the DLMPS approach. Tomographic images were reconstructed using the Feldkamp-Davis-Kress algorithm. Quantitative metrics including root-mean-square error (RMSE), peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM) were calculated in both the projection and image domains to evaluate the performance of the DLMPS approach. The DLMPS approach was compared with 11 state-of-the-art (SOTA) models, including CNN and Transformer architectures. For 1/4 sparse-view reconstruction task, the proposed DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0271, 45.93 dB, 0.9817, and 0.9587 in the projection domain, and 0.000885, 37.63 dB, 0.9074, and 0.9885 in the image domain, respectively. For 1/8 sparse-view reconstruction task, the DLMPS approach achieved averaged RMSE, PSNR, SSIM, and FSIM values of 0.0304, 44.85 dB, 0.9785, and 0.9524 in the projection domain, and 0.001057, 36.05 dB, 0.8786, and 0.9774 in the image domain, respectively. The DLMPS approach outperformed all the 11 SOTA models in both the projection and image domains for 1/4 and 1/8 sparse-view reconstruction tasks. The proposed DLMPS approach effectively improves the quality of sparse-view CBCT images in IGRT by accurately synthesizing missing projections, exhibiting potential in substantially reducing imaging dose to patients with minimal loss of image quality.

A Joint three-plane Physics-constrained Deep learning based Polynomial Fitting Approach for MR Electrical Properties Tomography.

Magnetic resonance electrical properties tomography can extract the electrical properties of in-vivo tissue. To estimate tissue electrical properties, various reconstruction algorithms have been proposed. However, physics-based reconstructions are prone to various artifacts such as noise amplification and boundary artifact. Deep learning-based approaches are robust to these artifacts but need extensive training datasets and suffer from generalization to unseen data. To address these issues, we introduce a joint three-plane physics-constrained deep learning framework for polynomial fitting MR-EPT by merging physics-based weighted polynomial fitting with deep learning. Within this framework, deep learning is used to discern the optimal polynomial fitting weights for a physics based polynomial fitting reconstruction on the complex B1+ data. For the prediction of optimal fitting coefficients, three neural networks were separately trained on simulated heterogeneous brain models to predict optimal polynomial weighting parameters in three orthogonal planes. Then, the network weights were jointly optimized to estimate the polynomial weights in each plane for a combined conductivity reconstruction. Based on this physics-constrained deep learning approach, we achieved an improvement of conductivity estimation accuracy in comparison to a single plane estimation and a reduction of computational load. The results demonstrate that the proposed method based on 3D data exhibits superior performance in comparison to conventional polynomial fitting methods in terms of capturing anatomical detail and homogeneity. Crucially, in-vivo application of the proposed method showed that the method generalizes well to in-vivo data, without introducing significant errors or artifacts. This generalization makes the presented method a promising candidate for use in clinical applications.

Exploring sentiment analysis in handwritten and E-text documents using advanced machine learning techniques: a novel approach

Traditionally, many people still wish to write on pen and paper. However, it has some drawbacks like accessing and storing physical documents efficiently, searching through them, and sharing them efficiently. Handwriting-to-text recognition classifies an individual’s handwriting and converts it into digital form. However, Handwriting Image to E-Text Conversion (HTC) removes all of the mentioned problems as it is easier to store, retrieve, and use the text as and when required. Emotions are a basic and very important aspect of anyone’s life. To understand this important aspect of an individual’s life, we have to detect emotions using affect data like text, voice, images, etc. This research work investigates the application of machine learning and deep learning methods in performing sentiment analysis on both handwritten and E-text statements. The primary objective of this research work is to distinguish the sentiment polarity and categorize it as positive, negative, or neutral while identifying emotion types such as happiness, sadness, surprise, fear, anger, disgust, and contempt. The study employs sophisticated methodologies to analyze handwritten image documents and E-text statements to provide a comprehensive understanding of sentiment nuances in diverse forms of communication. The authors proposed the Exploration of Sentiment Insights in Handwritten and E-text through Advanced Machine Learning (ESIHE_AML) algorithms-based model that finds the sentiment polarity and emotion types of handwritten text as well as E-Text. The results of the proposed model are described using various machine learning and deep learning-based approaches. Further, it significantly contributes to the advancements in sentiment analysis techniques and offers valuable insights into the emotional content present in both traditional and handwritten text formats. The proposed model shows higher accuracy (more than 90% in all cases) on standard bench mark datasets of Twitter, Kaggle, IAM, and Amazon reviews etc. It may further be increased by employing a hybrid approach of intelligent algorithms. This study highlights the adaptability of the ESIHE_AML algorithms-based model for analyzing sentiments in digital communication systems of the modern era.