Browse Items (14428 total)
Sort by:
-
Lung cancer detection and classification with optimal feature selection and two-fold-deep-learning-classifiers
The respiratory system is undoubtedly hampered by lung disorders. Also, one of the important reasons for death among people all around the world has been lung cancer. Early discovery can advance human survival probabilities. As a result, a unique ensemble-deep-learning paradigm for lung cancer detection and classification is established in the present research effort. The projected model includes five major phases: (a) image augmentation, (b) pre-processing, (c) segmentation, (d) feature extraction, (e) feature selection, and (f) lung cancer detection and classification, respectively. The collected raw CT images are augmentation with SMOTE. The augmented images are pre-processed via Median Filtering (for noise removal) and Contrast-limited adaptive histogram equalization (CLAHE) (for image contrast enhancement). Subsequently, from the pre-processed data, the ROI is identified via optimized U-NETS. The activation function (hyper-parameter) of U-NETS is optimized via a new hybrid optimization model-Digging Tunaswarm Optimizer (DTO). This DTO is the conceptual amalgamation of two standard meta-heuristic optimization models, namely Honey Badger Algorithm (HBA) and Tuna Swarm Optimization (TSO) models, respectively. Then, from the selected ROI area, the features like texture features (Manhattan Distance-based-GLCM, GLRM), Color features (Color Histogram), and Shape features (Moments, Area, Perimeter) are extracted. Among the extracted features, the optimal features are selected using DTO. This optimal feature selection reduces the computational complexity of the projected model. Finally, using these extracted optimal features, the two-fold-deep-learning-classifier framework is trained. This two-fold-deep-learning-classifiers framework encapsulates the Bidirectional long-short term memory (Bidirectional LSTM) and the Recurrent Neural Network (RNN) and the Modified Convolutional Neural Network (M-CNN). In the first phase, the Bi-LSTM and RNN are clamped, and they are trained with the selected optimal factors. The outcome from Bi-LSTM and also RNN was fed as input to M-CNN. Final detected findings based on the existence or absence of lung cancer are acquired from the M-CNN, whose loss function has been modified with RMSE. Finally, a comparative evaluation is undergone to validate the efficiency of the projected model. The proposed model has a higher overall accuracy (92.4%) detecting modelling accuracy (96.3%) and classification accuracy (92.4%) compared to other models such as HBA, TSO, CNN, 3D CenterNet, and TSCNN. The use of a two-fold deep learning framework is responsible for these improvements, and the model also has lower failure rates (FPR and FNR) in detecting lung cancer. It is suggested that the proposed approach is effective in early-stage lung cancer detection. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025. -
Lung cancer detection using image processing techniques
Lung cancer is one of the hazardous disease which leads to high death rates in the world. A cancer is an irregular growth of cells that can be characteristically derived from a single irregular cell and that may spread to whole part of the lung. So, it is necessary to find it at the earlier stages and take basic steps to cure.CT scan is one of the sensitive method used in the medical field for treating the patients. The quality of the image is very important for detection of lung cancer. Pre-processing of an image is a necessary process, as there is a difficulty in detecting cancer cells in an image due to the presence of noise and low-quality of images. To reduce the volume of these problems, diagnosis of lung cancer steps like image enhancement, image segmentation, feature extraction methods can be used. For processing and implementation of these methods Matlab tool has been used. This paper focuses on improving the quality of image and to optimise the work. Implementation is done using image processing toolbox that is available in Matlab tool.The whole idea of this research is to show the improved work in the existing system and to get more agreeable results. RJPT All right reserved. -
Lung Cancer Diagnosis from CT Images Based on Local Energy Based Shape Histogram (LESH) Feature Extration and Pre-processing
Lung cancer as of now is one of the dreaded diseases and it is destroying humanity never before. The mechanism of detecting the lung cancer will bring the level down of mortality and increase the life expectancy accuracy 13% from the detected cancer diagnosis from 24% of all cancer deaths. Although various methods are adopted to find the cancer, still there is a scope for improvement and the CT images are still preferred to find if there is any cancer in the body. The medical images are always a better one to find with the cancer in the human body. The proposed idea is, how we can improve the quality of the diagnosis form using pre-processing methods and Local energy shape histogram to improve the quality of the images. The deep learning methods are imported to find the varied results from the training process and finally to analyse the result. Medical examination is always part of our research and this result is always verified by the technicians. Major pre-processing techniques are used in this research work and they are discussed in this paper. The LESH technique is used to get better result in this research work and we will discuss how the image manipulation can be done to achieve better results from the CT images through various image processing methods. The construction of the proposed method will include smoothing of the images with median filters, enhancement of the image and finally segmentation of the images with LESH techniques. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Lung cancer prediction with advanced graph neural networks
This research aims to enhance lung cancer prediction using advanced machine learning techniques. The major finding is that integrating graph convolutional networks (GCNs) with graph attention networks (GATs) significantly improves predictive accuracy. The problem addressed is the need for early and accurate detection of lung cancer, leveraging a dataset from Kaggle's "Lung Cancer Prediction Dataset," which includes 309 instances and 16 attributes. The proposed A-GCN with GAT model is meticulously engineered with multiple layers and hidden units, optimized through hyperparameter adjustments, early stopping mechanisms, and Adam optimization techniques. Experimental results demonstrate the model's superior performance, achieving an accuracy of 0.9454, precision of 0.9213, recall of 0.9743, and an F1 score of 0.9482. These findings highlight the model's efficacy in capturing intricate patterns within patient data, facilitating early interventions and personalized treatment plans. This research underscores the potential of graph-based methodologies in medical research, particularly for lung cancer prediction, ultimately aiming to improve patient outcomes and survival rates through proactive healthcare interventions. 2025 Institute of Advanced Engineering and Science. All rights reserved. -
Lung cancer prediction with advanced graph neural networks
This research aims to enhance lung cancer prediction using advanced machine learning techniques. The major finding is that integrating graph convolutional networks (GCNs) with graph attention networks (GATs) significantly improves predictive accuracy. The problem addressed is the need for early and accurate detection of lung cancer, leveraging a dataset from Kaggle's "Lung Cancer Prediction Dataset," which includes 309 instances and 16 attributes. The proposed A-GCN with GAT model is meticulously engineered with multiple layers and hidden units, optimized through hyperparameter adjustments, early stopping mechanisms, and Adam optimization techniques. Experimental results demonstrate the model's superior performance, achieving an accuracy of 0.9454, precision of 0.9213, recall of 0.9743, and an F1 score of 0.9482. These findings highlight the model's efficacy in capturing intricate patterns within patient data, facilitating early interventions and personalized treatment plans. This research underscores the potential of graph-based methodologies in medical research, particularly for lung cancer prediction, ultimately aiming to improve patient outcomes and survival rates through proactive healthcare interventions. 2025 Institute of Advanced Engineering and Science. All rights reserved. -
Lung tuberculosis detection using x-ray images
This research work is based on the various experiments performed for the detection of lung tuberculosis using various methods like filtering, segmentation, feature extraction and classification. The results obtained from these experiments are discussed in this paper. Lung tuberculosis is a bacterial infection that causes more deaths in the world than any other infectious disease. Two billion people are infected with tuberculosis all around the world. Lung tuberculosis is a disease caused by a bacteria known as Mycobacterium tuberculosis or Tubercle bacillus. This research work strives to identify methods by which patients, who require second opinion for an already identified result, can save a lot of money. Once we receive X-ray image an input, pre-processing methods like Gaussian filter, median filter is applied. These filters help to remove unwanted noise and aid to get fine textural features. The output obtained from this is taken as an input and applied to water shed segmentation and gray level segmentation which helps to focus on the lung area of the obtained results. Output from these segmentation methods is fused to get a Region of Interest (ROI). From the ROI, the statistical features like area, major axis, minor axis, eccentricity, mean, kurtosis, skewness and entropy are extracted. Finally, we use KNN, Sequential minimal optimization (SMO), simple linear regression classification methods to detect lung tuberculosis. The results obtained in this paper suggests KNN classifier performs well than the other two classifiers. Research India Publications. -
LungDxNet: AI-Powered Low-Dose CT Analysis for Early Lung Cancer Detection
Early and accurate diagnosis, however, is still lacking for the most common form of lung cancer, and this remains one of the leading cancers leading to mortality. CT scans are widely used for lung cancer screening; however, their manual interpretation is time-consuming and prone to variability. This study introduces LungDxNet, a deep learning-based framework that integrates transfer learning to enhance diagnostic accuracy and efficiency. Using a large dataset of Low Dose CT (LDCT) scans, the system is built with fine-tuned pre-trained Convolutional Neural Networks (CNNs) such that feature extraction is reliable though minimal reducing radiation exposure. Consequently, LungDxNet involves the integration of component segmentation techniques that have been used to isolate the lung regions and discriminate the cancerous nodules from the malignant and benign cases. Very rigorous evaluations were performed on the model against both conventional machine learning and state of the art deep learning architectures. Results show that there is a substantial reduction of false positive and false negative resulting in a superior accuracy (98.88), sensitivity, and specificity. This design is to be scaled, robust and clinically applicable, making it a potential real world lung cancer diagnosis tool. Deep learning and transfer learning has excellent power to transform lung cancer detection, and this research brings awareness of how far we can optimise and integrate into clinical workflow. The model is enhanced for future work and adapted for real time diagnostic applications. 2025, Sakarya University. All rights reserved. -
Luxury consumption: The decision process
This chapter explores the luxury consumer decision process, highlighting the psychological, social, and cultural factors that influence luxury purchases. Consumers are driven by emotional and social motivations, such as self-expression and status, which shape their buying behaviors. Social and cultural differences require marketers to adapt strategies to diverse regional preferences. As digital technologies transform the luxury market, brands face the challenge of maintaining exclusivity while embracing e-commerce, social media, and influencer marketing. To remain competitive, luxury brands must leverage psychological insights and digital tools to create personalized, engaging experiences. The future of luxury consumption will depend on brands' ability to build meaningful connections with consumers, fostering loyalty and ensuring long-term success in an evolving market landscape. 2025, IGI Global Scientific Publishing. All rights reserved. -
Lyrics of longing: Exploring the role of music in the lived experience of homesickness among college students
The study investigates the multifaceted role of music during homesickness among first-year college students in India. As compared to other mental health outcomes, homesickness is a relatively understudied phenomenon, yet noteworthy due to its direct association with depression and anxiety. Although empirical evidence about music highlights its therapeutic potential for managing stress and anxiety, few studies have explored its role in connection with homesickness. The data for this study were collected through semi-structured interviews with 10 students about their perception of using music during homesickness. Through interpretative phenomenological analysis, the emerging themes pointed to a mixed influence, highlighting the bittersweet nature of music during homesickness. While music validates feelings and boosts confidence and motivation, it also triggers restorative nostalgia and serves as an escape from confronting homesickness. Moreover, native songs fostered an appreciation for ones culture and helped students connect with their roots. The study contributes to understanding how music is a versatile tool for students dealing with homesickness, offering solace and potential challenges. It serves as a guide to future intervention studies that could explore musics long-term influences. Recognising the diverse ways students perceive and respond to music provides valuable insights for developing tailored interventions and support systems. The Author(s) 2024. -
Lyrics of longing: Exploring the role of music in the lived experience of homesickness among college students
The study investigates the multifaceted role of music during homesickness among first-year college students in India. As compared to other mental health outcomes, homesickness is a relatively understudied phenomenon, yet noteworthy due to its direct association with depression and anxiety. Although empirical evidence about music highlights its therapeutic potential for managing stress and anxiety, few studies have explored its role in connection with homesickness. The data for this study were collected through semi-structured interviews with 10 students about their perception of using music during homesickness. Through interpretative phenomenological analysis, the emerging themes pointed to a mixed influence, highlighting the bittersweet nature of music during homesickness. While music validates feelings and boosts confidence and motivation, it also triggers restorative nostalgia and serves as an escape from confronting homesickness. Moreover, native songs fostered an appreciation for ones culture and helped students connect with their roots. The study contributes to understanding how music is a versatile tool for students dealing with homesickness, offering solace and potential challenges. It serves as a guide to future intervention studies that could explore musics long-term influences. Recognising the diverse ways students perceive and respond to music provides valuable insights for developing tailored interventions and support systems. The Author(s) 2024 -
m-quasi-?-Einstein contact metric manifolds
The goal of this article is to introduce and study the characterstics of m-quasi-?-Einstein metric on contact Riemannian manifolds. First, we prove that if a Sasakian manifold admits a gradient m-quasi-?-Einstein metric, then M is ?-Einstein and f is constant. Next, we show that in a Sasakian manifold if g represents an m-quasi-?-Einstein metric with a conformal vector field V, then V is Killing and M is ?-Einstein. Finally, we prove that if a non-Sasakian (?, )-contact manifold admits a gradient m-quasi-?-Einstein metric, then it is N(?)-contact metric manifold or a ?-Einstein. Kumara H.A., Venkatesha V., Naik D.M., 2022. -
Machinability and surface integrity for Mg AZ61A alloy composite by employing Taguchi integrated grey relational analysis
The present experimental study seeking to identify the optimal processing parameters in WEDM of Mg AZ61A-ZrB2 composite using Taguchi integrated grey relational analysis (GRA). Wire-cut electric discharge machining (WEDM) is the most effective method of metal removing process which is utilized in a variety of industries, like defence, biomedical, automotive, and aerospace. It is widely used in the machining of conductive and hard materials like composites and super alloys. In this experiment, the Mg AZ61A alloy composite reinforced with 12 wt% ZrB2 particles was fabricated through stir casting method. The scanning electron microscopy (SEM) with energy dispersive spectroscopy (EDS) mapping ensured the presence of matrix elements and reinforcement in the developed composite. The material removal rate (MRR) and surface roughness (Ra) were examined with relation to the processing factors such as pulse current (Ip), pulse on-time (Ton), and pulse off-time (Toff). The machining was conducted in compliance with Taguchi's L9 array. According to the GRA results, the optimal ranges of factors for achieving the better MRR and Ra were found at 4 amps of Ip, 15 ?s of Ton, and 45 ?s of Toff. The ANOVA results confirm that Ip was the most dominating factor that contributing to 37.58 %, next by Ton (30.96 %) and Toff (12.85 %), respectively. The confirmation test was demonstrated that the actual and predicted GRG values are fairly close to one another with 13.36 % improvement. The morphology of the machined surface was examined and it was shows the formation of a recast layer and the existence of flaws. 2025 The Authors -
Machine intelligence security : A methodological blend of fuzzy logic in industry 4.0 algorithms
The way things are made has changed a lot because of Industry 4.0. It has also led to a time with great technology and relationships. The paper discusses way to improve security in Machine Intelligence in the setting of Industry 4.0. The study uses a mix of methods to combine Fuzzy Logic with cutting-edge Industry 4.0 algorithms in order to deal with new hacking problems. Because fuzzy logic can deal with doubt and imprecision, it can be used to make current methods more reliable. This creates a complex and flexible security structure. The merger was carefully planned to make the methods for finding anomalies, reducing threats, and responding to incidents work better. The suggested method aims to make machine intelligence systems more resistant to complex cyber dangers by combining the best parts of Fuzzy Logic with Industry 4.0 algorithms. This study adds to the growing conversation about how to keep smart factory settings safe by focusing on a proactive and dynamic security model. The effects of this mix of methods could be felt in many different industries, making it possible to use advanced technologies in a safer and more reliable way in the age of Industry 4.0. 2024, Taru Publications. All rights reserved. -
Machine Intelligence: Computer Vision and Natural Language Processing
Machines are being systematically empowered to be interactive and intelligent in their operations, offerings. and outputs. There are pioneering Artificial Intelligence (AI) technologies and tools. Machine and Deep Learning (ML/DL) algorithms, along with their enabling frameworks, libraries, and specialized accelerators, find particularly useful applications in computer and machine vision, human machine interfaces (HMIs), and intelligent machines. Machines that can see and perceive can bring forth deeper and decisive acceleration, automation, and augmentation capabilities to businesses as well as people in their everyday assignments. Machine vision is becoming a reality because of advancements in the computer vision and device instrumentation spaces. Machines are increasingly software-defined. That is, vision-enabling software and hardware modules are being embedded in new-generation machines to be self-, surroundings, and situation-aware. Machine Intelligence emphasizes computer vision and natural language processing as drivers of advances in machine intelligence. The book examines these technologies from the algorithmic level to the applications level. It also examines the integrative technologies enabling intelligent applications in business and industry. Features: Motion images object detection over voice using deep learning algorithms Ubiquitous computing and augmented reality in HCI Learning and reasoning in Artificial Intelligence Economic sustainability, mindfulness, and diversity in the age of artificial intelligence and machine learning Streaming analytics for healthcare and retail domains Covering established and emerging technologies in machine vision, the book focuses on recent and novel applications and discusses state-of-the-art technologies and tools. 2024 Taylor & Francis Group, LLC. -
Machine Learning Algorithms for Optimizing Blockchain-Based Decentralized Autonomous Organizations
This research investigates the integration of machine learning algorithms within blockchain-based Decentralized Autonomous Organizations (DAOs) to enhance operational efficiency, resource allocation, decision-making, and governance. While DAOs provide a transparent and trustless mechanism for digital collaboration, they face challenges related to scalability, bias, data privacy, and coordination. We propose a novel framework that leverages supervises learning models for predictive analytics, reinforcement learning for autonomous decision-making, and unsupervised learning for anomaly detection in DAO voting and resource usage patterns. The study also addresses security and privacy risks by incorporating federated learning and homomorphic encryption. Our proposed model demonstrates improved throughput, decision accuracy, and fairness, as evidenced by performance benchmarks against traditional DAO implementations. The findings suggest that machine learning can significantly optimize DAO architecture and contribute to a more scalable, democratic, and intelligent decentralized ecosystem. 2025 IEEE. -
Machine Learning Algorithms for Prediction of Mobile Phone Prices
The drastic growth of technology helps us to reduce the man work in our day-to-day life. Especially mobile technology has a vital role in all areas of our lives today. This work focused on a data-driven method to estimate the price of a new smartphone by utilizing historical data on smartphone pricing, and key feature sets to build a model. Our goal was to forecast the cost of the phone by using a dataset with 21 characteristics related to price prediction. Logistic regression (LR), decision tree (DT), support vector machine (SVM), Naive Bayes algorithm (NB), K-nearest neighbor (KNN) algorithm, XGBoost, and AdaBoost are only a few of the popular machine learning techniques used for the prediction. The support vector machine achieved the highest accuracy (97%) compared to the other four classifiers we tested. K-nearest neighbors 94% accuracy was close to that of the support vector machine. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Machine Learning Algorithms for Predictive Maintenance in Hybrid Renewable Energy Microgrid Systems
The rapid expansion of hybrid renewable energy microgrid systems presents new challenges in maintaining system reliability and performance. This paper explores the application of machine learning algorithms for predictive maintenance in such systems, focusing on the early detection of potential failures to optimize operational efficiency and reduce downtime. By integrating real-time data from solar, wind, and storage components, the proposed models predict the remaining useful life (RUL) of critical components. The results demonstrate significant improvements in predictive accuracy, offering a robust solution for enhancing the reliability and longevity of renewable energy microgrids. The Authors, published by EDP Sciences. -
Machine Learning Algorithms for Stroke Risk Prediction Leveraging on Explainable Artificial Intelligence Techniques (XAI)
Stroke poses a significant global health challenge, contributing to widespread mortality and disability. Identifying predictors of stroke risk is crucial for enabling timely interventions, thereby reducing the increasing impact of strokes. This research addresses this imperative by employing Explainable Artificial Intelligence (XAI) techniques to pinpoint stroke risk predictors. To bridge existing gaps, six machine learning models were assessed using key performance metrics. Utilising the Synthetic Minority Over-sampling Technique (SMOTE) to minimize the impact of the imbalanced nature of the dataset used in this research, the Random Forest algorithm emerged as the most effective among the algorithms with an accuracy of 94.5%, AUC-ROC of 0.95, recall of 0.96, precision of 0.93, and an F1 score of 0.95. This study explored the interpretation of these algorithms and results using Local Interpretable Model-agnostic Explanations (LIME) and Explain Like I'm Five (ELI5). With the interpretations, healthcare providers can gain insight into patients' stroke risk predictions. Key stroke risk factors highlighted by the study include Age, Marital Status, Glucose Level, Body Mass Index, Work Type, Heart Disease, and Gender. This research significantly contributes to healthcare and healthcare informatics by providing insights that can enhance strategies for stroke prevention and management, ultimately leading to improved patient care. The identified predictors offer valuable information for healthcare professionals to develop targeted interventions, fostering a proactive approach to mitigating the impact of strokes on individuals and the healthcare system. 2024 IEEE. -
Machine Learning and Artificial Intelligence Techniques for Detecting Driver Drowsiness
The number of automobiles on the road grows in lockstep with the advancement of vehicle manufacturing. Road accidents appear to be on the rise, owing to this growing proliferation of vehicles. Accidents frequently occur in our daily lives, and are the top ten causes of mortality from injuries globally. It is now an important component of the worldwide public health burden. Every year, an estimated 1.2 million people are killed in car accidents. Driver drowsiness and weariness are major contributors to traffic accidents this study relies on computer software and photographs, as well as a Convolutional Neural Network (CNN), to assess whether a motorist is tired. The Driver Drowsiness System is built on the Multi-Layer Feed-Forward Network concept CNN was created using around 7,000 photos of eyes in both sleepiness and non-drowsiness phases with various face layouts. These photos were divided into two datasets: training (80% of the images) and testing (20% of the images). For training purposes, the pictures in the training dataset are fed into the network. To decrease information loss as much as feasible, backpropagation techniques and optimizers are applied. We developed an algorithm to calculate ROI as well as track and evaluate motor and visual impacts. 2022 Boppuru Rudra Prathap et al., published by Sciendo. -
Machine Learning and Artificial Intelligence Techniques for Detecting Driver Drowsiness
The number of automobiles on the road grows in lock-step with the advancement of vehicle manufacturing. Road accidents appear to be on the rise, owing to this growing proliferation of vehicles. Accidents frequently occur in our daily lives, and are the top ten causes of mortality from injuries globally. It is now an important component of the worldwide public health burden. Every year, an estimated 1.2 million people are killed in car ac-cidents. Driver drowsiness and weariness are major con-tributors to traffic accidents this study relies on computer software and photographs, as well as a Convolutional Neural Network (CNN), to assess whether a motorist is tired. The Driver Drowsiness System is built on the Multi-Layer Feed-Forward Network concept CNN was created using around 7,000 photos of eyes in both sleepiness and non-drowsiness phases with various face layouts. These photos were divided into two datasets: training (80% of the images) and testing (20% of the images). For training purposes, the pictures in the training dataset are fed into the network. To decrease information loss as much as feasible, backpropagation techniques and optimizers are applied. We developed an algorithm to calculate ROI as well as track and evaluate motor and visual impacts. 2022, Industrial Research Institute for Automation and Measurements. All rights reserved.